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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -conscious
    -0.07
     soar
    -0.06
     scre
    -0.06
     случ
    -0.06
    ücret
    -0.06
     spoiled
    -0.06
     hovered
    -0.06
    atisation
    -0.06
    скільки
    -0.06
     임
    -0.06
    POSITIVE LOGITS
     MainForm
    0.07
    apanese
    0.06
    \Models
    0.06
     religious
    0.06
     Angelo
    0.06
     Dante
    0.06
     cosplay
    0.06
     Malone
    0.06
    _FORCE
    0.06
     Delegate
    0.06
    Act Density 0.000%

    No Known Activations