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

    Neuronpedia

    INDEX
    Explanations

    Nova

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counted
    -0.07
     Mouth
    -0.07
     criticism
    -0.07
    >P
    -0.07
     Grim
    -0.07
    _mr
    -0.06
    Bring
    -0.06
     Bro
    -0.06
    text
    -0.06
    /mm
    -0.06
    POSITIVE LOGITS
     vystav
    0.07
    (guild
    0.06
    akespeare
    0.06
    华
    0.06
     Microsystems
    0.06
     newState
    0.06
    =node
    0.06
    erguson
    0.06
     saya
    0.06
    _inches
    0.06
    Act Density 0.002%

    No Known Activations