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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Smooth
    -0.06
    _Construct
    -0.06
    _SCHEDULE
    -0.06
    اخل
    -0.06
    Effects
    -0.06
    .PARAM
    -0.06
    משלוח
    -0.06
    /Input
    -0.06
     Mouth
    -0.06
    -0.06
    POSITIVE LOGITS
    ש
    0.08
     peoples
    0.08
     nihil
    0.07
     happiness
    0.07
    得以
    0.07
    �
    0.07
     xc
    0.07
    ﻬ
    0.07
     alguém
    0.07
     została
    0.07
    Act Density 0.010%

    No Known Activations