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

    Neuronpedia

    INDEX
    Explanations

    modal verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     op
    -0.06
     خواه
    -0.06
    (vp
    -0.06
     jobs
    -0.06
    (reason
    -0.06
    _green
    -0.06
     bundle
    -0.06
    _tr
    -0.06
    (actions
    -0.06
    probability
    -0.06
    POSITIVE LOGITS
    بدأ
    0.07
    orial
    0.07
    -floor
    0.07
    achusetts
    0.06
     федераль
    0.06
     Männer
    0.06
     pute
    0.06
    [:,:,
    0.06
    rün
    0.06
    chief
    0.06
    Act Density 0.162%

    No Known Activations