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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otic
    -0.07
    لیه
    -0.07
    ails
    -0.07
    (strtolower
    -0.06
     summon
    -0.06
    Daemon
    -0.06
     पहच
    -0.06
    Bindable
    -0.06
    Virginia
    -0.06
    athroom
    -0.06
    POSITIVE LOGITS
    ARSER
    0.06
     screws
    0.06
    ℃
    0.06
    iap
    0.06
    职
    0.06
     refuse
    0.06
     الجز
    0.06
    .:
    0.06
     çalışma
    0.06
     sleeves
    0.06
    Act Density 0.030%

    No Known Activations