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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	on
    -0.07
     mise
    -0.07
     дл
    -0.07
    딱
    -0.07
     pleaded
    -0.07
    	cv
    -0.07
    各家
    -0.07
    ൽ
    -0.07
    ます
    -0.07
    ,in
    -0.07
    POSITIVE LOGITS
    怒
    0.07
     overload
    0.07
    _stack
    0.07
     Remote
    0.07
     folds
    0.07
     attacker
    0.06
     nhiệt
    0.06
    高端
    0.06
     regardless
    0.06
    BufferSize
    0.06
    Act Density 0.001%

    No Known Activations