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

    Neuronpedia

    INDEX
    Explanations

    μ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     downhill
    -0.07
    Fund
    -0.07
     grids
    -0.06
     outer
    -0.06
     cycles
    -0.06
     affine
    -0.06
     aggression
    -0.06
    _fps
    -0.06
     rho
    -0.06
    double
    -0.06
    POSITIVE LOGITS
    UU
    0.07
    Cheers
    0.07
     Nếu
    0.07
    розум
    0.07
    quito
    0.06
    buf
    0.06
    _pc
    0.06
    consult
    0.06
    .OS
    0.06
    .DataGridView
    0.06
    Act Density 0.009%

    No Known Activations