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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roberto
    -0.07
    seud
    -0.07
     (_,
    -0.07
     Zug
    -0.06
     öngör
    -0.06
     elevator
    -0.06
     Provid
    -0.06
     southwestern
    -0.06
    ��
    -0.06
    .ManyToMany
    -0.06
    POSITIVE LOGITS
    _label
    0.07
     staff
    0.07
     synd
    0.07
    aille
    0.06
     Gardens
    0.06
     __________________
    0.06
    ูก
    0.06
    Exposed
    0.06
    (__
    0.06
    �
    0.06
    Act Density 0.018%

    No Known Activations