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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Candid
    -0.07
    ��
    -0.07
    ('?
    -0.07
     facts
    -0.07
     CV
    -0.07
     суду
    -0.07
    getResource
    -0.06
    ==============
    -0.06
    جاد
    -0.06
     longer
    -0.06
    POSITIVE LOGITS
    	struct
    0.06
     giúp
    0.06
     minul
    0.06
    $h
    0.06
    Urban
    0.06
    Uh
    0.06
     Chic
    0.06
    noinspection
    0.06
    _math
    0.06
    ░
    0.06
    Act Density 0.001%

    No Known Activations