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

    Neuronpedia

    INDEX
    Explanations

    conversational/personal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sert
    -0.06
     onslaught
    -0.06
     groom
    -0.06
     endemic
    -0.06
     Clock
    -0.06
    Clock
    -0.06
     ugly
    -0.06
     hare
    -0.06
     случай
    -0.06
    荷
    -0.06
    POSITIVE LOGITS
    localObject
    0.08
    _COLUMNS
    0.07
    setq
    0.07
    _theta
    0.07
    _Z
    0.07
     něj
    0.07
    _makeConstraints
    0.06
    �
    0.06
    ɵ
    0.06
    meleri
    0.06
    Act Density 0.272%

    No Known Activations