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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tern
    -0.07
    (symbol
    -0.07
     factors
    -0.06
    imo
    -0.06
    ثار
    -0.06
    >[↵
    -0.06
    orias
    -0.06
     GH
    -0.06
     Дем
    -0.06
     waterfall
    -0.06
    POSITIVE LOGITS
    �
    0.07
     susceptible
    0.07
    .stem
    0.06
    wpdb
    0.06
    Birthday
    0.06
     Sanity
    0.06
    ()):
    0.06
     승
    0.06
    shm
    0.06
     Ή
    0.06
    Act Density 0.057%

    No Known Activations