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

    Neuronpedia

    INDEX
    Explanations

    interrogative and causative phrases related to actions and events

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

    new physics, somebody was, killer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mécan
    -0.38
     comprensión
    -0.38
    UnusedPrivate
    -0.37
    WithMany
    -0.36
     perspek
    -0.36
     montón
    -0.35
     propOrder
    -0.34
     prévue
    -0.33
     salvación
    -0.33
     wz
    -0.33
    POSITIVE LOGITS
    EDEFAULT
    0.59
    kháu
    0.56
    ruptedException
    0.52
    Diweddarwch
    0.47
     Chwiliwch
    0.45
     Numerade
    0.45
    ंदीखरीदारी
    0.45
    المكان
    0.45
     externas
    0.44
    ValueStyle
    0.43
    Act Density 0.021%

    No Known Activations