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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gorit
    -0.07
    analy
    -0.06
     inequalities
    -0.06
     parad
    -0.06
     Pai
    -0.06
    Pan
    -0.06
    /mat
    -0.06
    _categorical
    -0.06
    Tek
    -0.06
     usuario
    -0.06
    POSITIVE LOGITS
     SAVE
    0.07
     separate
    0.07
     extensive
    0.06
    .REACT
    0.06
     Preparation
    0.06
     asserting
    0.06
     cared
    0.06
     بط
    0.06
     wow
    0.06
    getResponse
    0.06
    Act Density 0.014%

    No Known Activations