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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SOFTWARE
    -0.06
    ////////////////////////////////////////////////////////////
    -0.06
     �
    -0.06
    _city
    -0.06
    一页
    -0.06
    	size
    -0.05
    <_
    -0.05
    RN
    -0.05
     bombings
    -0.05
     अन
    -0.05
    POSITIVE LOGITS
    жи
    0.08
    alfa
    0.07
    ("&
    0.07
    ж
    0.07
    prepare
    0.07
     пере
    0.07
    ubby
    0.07
    .prepare
    0.07
     reliable
    0.06
    lettes
    0.06
    Act Density 0.000%

    No Known Activations