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

    Neuronpedia

    INDEX
    Explanations

    court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    purchase
    -0.08
    greater
    -0.07
    wen
    -0.07
    .instructions
    -0.07
    Ps
    -0.07
    _written
    -0.07
     Input
    -0.06
    /of
    -0.06
    _capture
    -0.06
    ή
    -0.06
    POSITIVE LOGITS
    ERVE
    0.06
     munch
    0.06
    agnet
    0.06
     porta
    0.06
     incididunt
    0.06
    .jsdelivr
    0.06
     estar
    0.06
    chied
    0.06
     RPG
    0.06
     Mohammad
    0.06
    Act Density 0.001%

    No Known Activations