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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Variable
    -0.07
     UserDao
    -0.07
    _rotate
    -0.07
    _write
    -0.07
     chan
    -0.06
    _exit
    -0.06
     King
    -0.06
    Emer
    -0.06
     Hammer
    -0.06
    	parent
    -0.06
    POSITIVE LOGITS
    FLICT
    0.07
     ROUT
    0.06
    дают
    0.06
    /github
    0.06
    _SSL
    0.06
     policym
    0.06
     disliked
    0.06
    лек
    0.06
    ший
    0.06
     liver
    0.06
    Act Density 0.030%

    No Known Activations