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
    incre
    -0.07
     purs
    -0.07
    ็ม
    -0.07
     phủ
    -0.07
    .integration
    -0.06
    Targets
    -0.06
    122
    -0.06
    _POINT
    -0.06
    된다
    -0.06
     commentators
    -0.06
    POSITIVE LOGITS
     performed
    0.06
     november
    0.06
     ($.
    0.06
     insider
    0.06
    -picker
    0.06
     flawless
    0.06
    ('/');↵
    0.06
    (passport
    0.05
    ])*
    0.05
    .damage
    0.05
    Act Density 0.010%

    No Known Activations