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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helpless
    -0.06
    Against
    -0.06
     ragazze
    -0.06
     إليه
    -0.06
     Saud
    -0.06
    {},
    -0.06
     Pay
    -0.06
    ......↵↵
    -0.06
     Visa
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ться
    0.07
    ATORY
    0.07
    ±n
    0.07
    (audio
    0.07
     (((
    0.07
    .ct
    0.06
    perimental
    0.06
    shall
    0.06
     ((
    0.06
    [(
    0.06
    Act Density 0.048%

    No Known Activations