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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indy
    -0.07
    restaurant
    -0.07
     yacc
    -0.07
    ?#
    -0.07
     infiltr
    -0.06
    _thresh
    -0.06
    etics
    -0.06
    asis
    -0.06
     MILF
    -0.06
     PSA
    -0.06
    POSITIVE LOGITS
    .hxx
    0.07
     contentious
    0.07
    редел
    0.06
     Frag
    0.06
    _charset
    0.06
    isSelected
    0.06
     robust
    0.06
     sag
    0.06
     discrimin
    0.06
    jectory
    0.06
    Act Density 0.001%

    No Known Activations