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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     communal
    -0.09
     civic
    -0.07
    klä
    -0.06
     consort
    -0.06
     beam
    -0.06
    Nota
    -0.06
     instrumental
    -0.06
     proceso
    -0.06
     čá
    -0.06
     style
    -0.06
    POSITIVE LOGITS
    clusions
    0.06
    LK
    0.06
     ран
    0.06
    eview
    0.06
    ITTER
    0.06
    entries
    0.05
    .other
    0.05
    HD
    0.05
    errer
    0.05
    aurant
    0.05
    Act Density 0.010%

    No Known Activations