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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     electrodes
    -0.08
     die
    -0.07
    CONTROL
    -0.07
     Die
    -0.07
     clave
    -0.06
    128
    -0.06
    Die
    -0.06
    973
    -0.06
    achu
    -0.06
    ientes
    -0.06
    POSITIVE LOGITS
     a
    0.09
     an
    0.07
    -even
    0.06
    ,a
    0.06
     �
    0.06
    '],$_
    0.06
     paperback
    0.06
    ْع
    0.06
    openh
    0.06
     infringement
    0.06
    Act Density 0.033%

    No Known Activations