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

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Born
    -0.08
     Shall
    -0.06
     yayın
    -0.06
    Pg
    -0.06
     Hank
    -0.06
     qty
    -0.06
     sonunda
    -0.06
    xlabel
    -0.06
    976
    -0.05
     QE
    -0.05
    POSITIVE LOGITS
    igner
    0.08
    Animator
    0.07
    angler
    0.07
    emple
    0.07
     characterize
    0.07
     vibration
    0.07
    .attribute
    0.07
    定的
    0.06
    (hand
    0.06
    (from
    0.06
    Act Density 0.001%

    No Known Activations