Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to electrostatic devices and their functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    electricity and electric charge

    np_acts-logits-general · gemini-2.0-flash

    electric and electrostatic charge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     엔
    -0.61
     excise
    -0.56
    rollers
    -0.53
     Spicer
    -0.52
    ATIVES
    -0.51
     démo
    -0.51
    rowser
    -0.50
    roller
    -0.50
     Hür
    -0.49
    سع
    -0.49
    POSITIVE LOGITS
     electric
    1.26
     electrical
    1.23
     electricity
    1.17
     Electric
    1.12
     ELECTRO
    1.09
    ELECT
    1.09
     ELECTRIC
    1.09
     electro
    1.08
     Electro
    1.08
    electric
    1.08
    Act Density 0.675%

    No Known Activations