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

    Neuronpedia

    INDEX
    Explanations

    Names and places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _funcs
    -0.08
     fontWeight
    -0.07
    control
    -0.07
     swallowed
    -0.06
     ihtiy
    -0.06
     producto
    -0.06
     chairs
    -0.06
     thanked
    -0.06
     wellbeing
    -0.06
     جل
    -0.06
    POSITIVE LOGITS
    culator
    0.07
    REP
    0.07
    reno
    0.06
    Progress
    0.06
     gps
    0.06
     Rox
    0.06
     Crypt
    0.06
     kend
    0.06
     ΚΑΙ
    0.06
    .question
    0.06
    Act Density 0.006%

    No Known Activations