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

    Neuronpedia

    INDEX
    Explanations

    intrinsic value and risk assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rices
    0.45
    og
    0.44
    igle
    0.41
    iggle
    0.39
     cél
    0.37
     (
    0.36
     নে
    0.36
    urable
    0.36
    ircle
    0.36
    urals
    0.36
    POSITIVE LOGITS
    സിന്
    0.40
    খ
    0.39
     LOCCTR
    0.39
    ús
    0.38
    اسة
    0.38
     Pillars
    0.38
    ErrorException
    0.37
    łada
    0.37
    tidak
    0.37
    },-\
    0.37
    Act Density 0.001%

    No Known Activations