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

    Neuronpedia

    INDEX
    Explanations

    coward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    incinn
    -0.07
    邪
    -0.07
    (uri
    -0.06
    teş
    -0.06
    NSDate
    -0.06
     showMessage
    -0.06
    (slug
    -0.06
    esch
    -0.06
    їна
    -0.06
     myster
    -0.06
    POSITIVE LOGITS
     coward
    0.09
     retiring
    0.07
     rnn
    0.07
    Coming
    0.07
     Received
    0.07
    Kids
    0.06
     coming
    0.06
     wanted
    0.06
    Claims
    0.06
     EQ
    0.06
    Act Density 0.011%

    No Known Activations