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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /view
    -0.07
    קום
    -0.07
    땃
    -0.07
    ieme
    -0.07
    dump
    -0.06
     Kostenlose
    -0.06
    Party
    -0.06
    kg
    -0.06
     Girlfriend
    -0.06
    土
    -0.06
    POSITIVE LOGITS
     specializes
    0.09
    Politics
    0.08
    caster
    0.07
     inicial
    0.07
     nécess
    0.07
    马上就
    0.07
     Cheney
    0.07
    菖
    0.07
     Tick
    0.07
    (category
    0.06
    Act Density 0.003%

    No Known Activations