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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autofocus
    -0.07
     распред
    -0.06
    овари
    -0.06
     Butt
    -0.06
    xxxx
    -0.06
    /tutorial
    -0.06
     Concent
    -0.06
    овані
    -0.06
    �
    -0.06
     соз
    -0.06
    POSITIVE LOGITS
    _eff
    0.07
    _register
    0.06
     \
↵
    0.06
    _terms
    0.06
    Stats
    0.06
    виг
    0.06
     shops
    0.06
     Premi
    0.06
     ounce
    0.06
    _Open
    0.06
    Act Density 0.012%

    No Known Activations