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

    Neuronpedia

    INDEX
    Explanations

    @param, @return, @throws in documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shines
    0.42
     indústria
    0.38
    uak
    0.37
    :"))
    0.37
    :\
    0.36
    *:
    0.36
     :\
    0.36
     industry
    0.36
     நுண்ண
    0.36
     stimmt
    0.36
    POSITIVE LOGITS
     @
    0.94
    @
    0.76
     {@
    0.55
     @_
    0.54
    /@
    0.52
    ,@
    0.50
    }@
    0.50
    .@
    0.48
     //@
    0.46
    @{
    0.46
    Act Density 0.002%

    No Known Activations