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

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantifications related to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical quantities and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.42
    IBAction
    -0.37
    noindent
    -0.36
     Forced
    -0.35
    LOYEES
    -0.34
    ueba
    -0.34
    ποίη
    -0.33
    новниш
    -0.33
     участ
    -0.33
     touched
    -0.33
    POSITIVE LOGITS
     dizaines
    0.71
    hundreds
    0.69
     Hundreds
    0.68
     hundreds
    0.67
     ratusan
    0.66
    thousands
    0.66
     decenas
    0.65
    Hundreds
    0.65
     cientos
    0.64
     dizaine
    0.63
    Act Density 0.048%

    No Known Activations