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

    Neuronpedia

    INDEX
    Explanations

    mixing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Release
    -0.07
     Cruise
    -0.07
     Rw
    -0.07
    学生
    -0.06
    Erreur
    -0.06
    鞋
    -0.06
    @click
    -0.06
    .reject
    -0.06
     Pazar
    -0.06
     Ud
    -0.06
    POSITIVE LOGITS
    pun
    0.07
    _CHILD
    0.07
     галузі
    0.07
     defaultManager
    0.07
    IRONMENT
    0.07
    _COMPANY
    0.06
    .kotlin
    0.06
     selective
    0.06
    }?
    0.06
     быстро
    0.06
    Act Density 0.005%

    No Known Activations