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

    Neuronpedia

    INDEX
    Explanations

    shake a stick at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ba
    -0.07
    uelles
    -0.06
     Bass
    -0.06
    roph
    -0.06
     gw
    -0.06
     expectancy
    -0.06
    _ab
    -0.06
    ias
    -0.06
     "***
    -0.06
    _box
    -0.06
    POSITIVE LOGITS
     poisoning
    0.07
     rempl
    0.06
     conditioned
    0.06
    \uC
    0.06
     страх
    0.06
     tore
    0.06
    LEN
    0.06
     wakeup
    0.06
    �
    0.06
    .SET
    0.06
    Act Density 0.000%

    No Known Activations