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

    Neuronpedia

    INDEX
    Explanations

    variable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chamber
    -0.08
     illusions
    -0.08
     commend
    -0.08
    �
    -0.08
    -0.07
     indis
    -0.07
    व्य
    -0.07
     chamber
    -0.07
     seren
    -0.07
     आत
    -0.07
    POSITIVE LOGITS
     fed
    0.08
     Kop
    0.07
    <number
    0.07
     inad
    0.07
     mas
    0.07
     incon
    0.07
     siv
    0.07
     Mas
    0.07
    jh
    0.07
    ij
    0.07
    Act Density 0.250%
    No Known Activations