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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     schwer
    -0.08
     güç
    -0.06
     grouping
    -0.06
     clas
    -0.06
     अगल
    -0.06
    Hugh
    -0.06
     přesně
    -0.06
    realm
    -0.06
     grouped
    -0.06
     dequeueReusableCellWithIdentifier
    -0.06
    POSITIVE LOGITS
    ことが
    0.07
    REV
    0.07
     دوست
    0.07
    <num
    0.07
     ENV
    0.06
    _ALIGN
    0.06
     Moment
    0.06
    ancia
    0.06
    IRR
    0.06
    ----</
    0.06
    Act Density 0.067%

    No Known Activations