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

    Neuronpedia

    INDEX
    Explanations

    Law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpos
    -0.07
     جامع
    -0.07
     hatten
    -0.07
    �
    -0.06
     chimpan
    -0.06
    thumb
    -0.06
     sehen
    -0.06
     werd
    -0.06
    ビ
    -0.06
    xffffffff
    -0.06
    POSITIVE LOGITS
    old
    0.06
     repairs
    0.06
    UIButton
    0.06
    (UnityEngine
    0.06
     Robotics
    0.06
    .Exec
    0.06
    ydro
    0.06
    (sql
    0.06
    _audio
    0.06
    _hw
    0.06
    Act Density 0.014%

    No Known Activations