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

    Neuronpedia

    INDEX
    Explanations

    approximately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sel
    -0.08
    256
    -0.07
    7
    -0.07
     Behind
    -0.07
     zombie
    -0.07
     cops
    -0.07
     withd
    -0.07
     Lords
    -0.07
     DVDs
    -0.06
     born
    -0.06
    POSITIVE LOGITS
     Approximately
    0.10
    ）。↵
    0.07
    олее
    0.07
    onacci
    0.07
    çı
    0.07
    ：↵↵
    0.07
    :
    0.07
     approximately
    0.07
    .cum
    0.07
     prueba
    0.07
    Act Density 0.009%

    No Known Activations