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

    Neuronpedia

    INDEX
    Explanations

    Written reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    甫
    -0.07
     hız
    -0.07
     Guidelines
    -0.07
    _Status
    -0.07
     Modes
    -0.07
     morb
    -0.07
     años
    -0.07
    emoji
    -0.07
     /*----------------------------------------------------------------
    -0.06
     theorem
    -0.06
    POSITIVE LOGITS
     subscriptions
    0.07
    YLON
    0.07
    ่าย
    0.06
     carga
    0.06
     receipts
    0.06
    שכר
    0.06
     RK
    0.06
    participant
    0.06
    lg
    0.06
    PTS
    0.06
    Act Density 0.067%

    No Known Activations