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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantities, measurements, and procedural specifications

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

    amounts, requirements, or dose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chham
    -0.44
    AndEndTag
    -0.43
     Se
    -0.41
    Omega
    -0.40
    ipan
    -0.40
     ban
    -0.39
    ita
    -0.39
     inten
    -0.39
     reg
    -0.39
    Se
    -0.38
    POSITIVE LOGITS
     ModelRenderer
    0.56
    Література
    0.54
     Infór
    0.52
     Inscrivez
    0.52
     avoient
    0.51
     enfans
    0.50
     récompenses
    0.48
     GenerationType
    0.48
     feroit
    0.48
     pouvoit
    0.48
    Act Density 0.168%

    No Known Activations