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

    Neuronpedia

    INDEX
    Explanations

    viability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proceso
    -0.07
    	en
    -0.07
    razy
    -0.06
    الق
    -0.06
    ูงส
    -0.06
    يفة
    -0.06
    @js
    -0.06
    -fit
    -0.06
     cabinet
    -0.06
    фектив
    -0.06
    POSITIVE LOGITS
    .model
    0.06
     fm
    0.06
    '],$_
    0.06
    ึก
    0.06
    charted
    0.06
    (Cl
    0.06
     distractions
    0.06
    _quiz
    0.06
     confidently
    0.06
    decoded
    0.06
    Act Density 0.022%

    No Known Activations