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

    Neuronpedia

    INDEX
    Explanations

    interviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /my
    -0.07
    ely
    -0.07
    .Hash
    -0.06
     cheg
    -0.06
    accur
    -0.06
    feel
    -0.06
     đều
    -0.06
    esc
    -0.06
    (adj
    -0.06
    國家
    -0.06
    POSITIVE LOGITS
     Nunes
    0.08
    داد
    0.07
    imers
    0.07
    .Categories
    0.07
    alf
    0.06
     congest
    0.06
     strtok
    0.06
    probante
    0.06
    _label
    0.06
    ,S
    0.06
    Act Density 0.070%

    No Known Activations