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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     içine
    -0.06
    crime
    -0.06
     cause
    -0.06
     센
    -0.06
     ersten
    -0.06
    ileges
    -0.06
     medicine
    -0.06
    Sender
    -0.06
     نوش
    -0.06
    severity
    -0.06
    POSITIVE LOGITS
    štění
    0.07
    ftime
    0.07
    isty
    0.06
    inges
    0.06
    (gl
    0.06
    continue
    0.06
    ського
    0.06
     iterative
    0.06
    Disposable
    0.06
     фундамент
    0.06
    Act Density 0.025%

    No Known Activations