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

    Neuronpedia

    INDEX
    Explanations

    abstract topic specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    缑
    0.41
     tepi
    0.40
     arugula
    0.38
     lavar
    0.38
    不是
    0.37
     principalTable
    0.37
     capitol
    0.37
     apar
    0.37
    设备的
    0.37
    调
    0.36
    POSITIVE LOGITS
     upto
    0.78
     irrespective
    0.76
     till
    0.72
    till
    0.70
     availed
    0.63
    Hence
    0.61
     hence
    0.61
    Till
    0.59
     erstwhile
    0.59
     Hence
    0.56
    Act Density 0.007%

    No Known Activations