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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Isaiah
    -0.07
     guard
    -0.06
     suppression
    -0.06
     Foo
    -0.06
     ذلك
    -0.06
     Battle
    -0.06
    _tuple
    -0.06
     shields
    -0.06
     bánh
    -0.06
     bab
    -0.06
    POSITIVE LOGITS
     +
    0.13
    +
    0.10
    +\
    0.09
    )+
    0.08
    +s
    0.07
    "+
    0.07
    _WM
    0.07
    ]+
    0.07
    :+
    0.07
    ('+
    0.07
    Act Density 0.114%

    No Known Activations