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

    Neuronpedia

    INDEX
    Explanations

    diagnosis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StartupScript
    -0.07
     Suk
    -0.07
     Kag
    -0.07
    CellStyle
    -0.06
    xDE
    -0.06
     Waves
    -0.06
     발매
    -0.06
     Dev
    -0.06
    ’ta
    -0.06
     pochop
    -0.06
    POSITIVE LOGITS
     clientele
    0.07
     doubtful
    0.06
     subscribe
    0.06
    (vertex
    0.06
    <p
    0.06
     phosph
    0.06
     line
    0.06
    민
    0.06
     legislation
    0.06
    613
    0.06
    Act Density 0.004%

    No Known Activations