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

    Neuronpedia

    INDEX
    Explanations

    za

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _boot
    -0.08
    suite
    -0.06
     Coh
    -0.06
    脱
    -0.06
    .twimg
    -0.06
    roken
    -0.06
     Nir
    -0.06
    оби
    -0.06
    rawl
    -0.06
     Ducks
    -0.06
    POSITIVE LOGITS
     taxpayers
    0.08
     roaming
    0.07
    医疗
    0.06
    .Template
    0.06
     resurrection
    0.06
     stakeholders
    0.06
    场
    0.06
    ropped
    0.06
     alternatives
    0.06
     takové
    0.06
    Act Density 0.000%

    No Known Activations