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

    Neuronpedia

    INDEX
    Explanations

    whether

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cmds
    -0.07
    Ace
    -0.06
    Script
    -0.06
    865
    -0.06
    165
    -0.06
     IPA
    -0.06
    ').'
    -0.06
    FSIZE
    -0.06
     clipboard
    -0.06
    "urls
    -0.06
    POSITIVE LOGITS
     whether
    0.10
     Whether
    0.08
    whether
    0.08
    Whether
    0.08
    �
    0.08
    her
    0.07
     vag
    0.07
    _through
    0.07
    тах
    0.07
    ?</
    0.07
    Act Density 0.019%

    No Known Activations