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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entweder
    -0.84
     autorytatywna
    -0.83
    findpost
    -0.81
     either
    -0.80
    ITHER
    -0.75
    GOTREF
    -0.72
    either
    -0.71
    principalColumn
    -0.69
     nakalista
    -0.68
    Either
    -0.66
    POSITIVE LOGITS
     a
    0.68
    ,
    0.61
    "',
    0.40
     vein
    0.38
    WARNING
    0.38
    <eos>
    0.37
     zalo
    0.37
    jface
    0.37
     romanzo
    0.37
     až
    0.36
    Act Density 0.052%

    No Known Activations