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

    Neuronpedia

    INDEX
    Explanations

    Mind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ervals
    -0.07
    irus
    -0.07
    renom
    -0.06
    biology
    -0.06
    ircon
    -0.06
     علت
    -0.06
     yapı
    -0.06
    jylland
    -0.06
    ighthouse
    -0.06
     Zhang
    -0.06
    POSITIVE LOGITS
    wrapper
    0.07
     partnership
    0.06
     Tart
    0.06
    .panel
    0.06
     pont
    0.06
     oppos
    0.06
     coord
    0.06
    前
    0.06
     sockets
    0.06
     pdf
    0.06
    Act Density 0.000%

    No Known Activations