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

    Neuronpedia

    INDEX
    Explanations

    imes/times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invariant
    -0.08
     pill
    -0.07
    Info
    -0.07
     Leads
    -0.07
     Extended
    -0.07
     Sq
    -0.07
     wee
    -0.07
     конф
    -0.07
     other
    -0.07
    viewModel
    -0.07
    POSITIVE LOGITS
    LOUR
    0.07
    .sulake
    0.07
    мот
    0.06
    PreferredGap
    0.06
    .tie
    0.06
    .stem
    0.06
    Cert
    0.06
    ween
    0.06
    させ
    0.06
     наприклад
    0.05
    Act Density 0.005%

    No Known Activations