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

    Neuronpedia

    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     migrant
    -0.08
     storia
    -0.07
    了自己的
    -0.07
     habe
    -0.07
     vier
    -0.07
    TMP
    -0.07
    ɂ
    -0.07
     anomal
    -0.07
    _signed
    -0.07
     lapse
    -0.07
    POSITIVE LOGITS
    -loving
    0.08
    ectar
    0.07
    AuthService
    0.07
     gözü
    0.07
    溍
    0.07
     cleanliness
    0.07
     drunken
    0.07
    PushButton
    0.07
    Escort
    0.07
     Erotic
    0.07
    Act Density 0.195%

    No Known Activations