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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 'K', often followed by hyphens and numbers

    oai_token-act-pair · gemini-2.0-flash

    K

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __':
    -0.79
    rungsseite
    -0.68
    __':
    -0.66
    __":
    -0.65
    EndContext
    -0.63
    componentDid
    -0.59
     useCallback
    -0.59
     kasarigan
    -0.59
    httphttps
    -0.58
    الإنجليزية
    -0.57
    POSITIVE LOGITS
    monary
    0.49
    canyon
    0.44
     Sensi
    0.44
    InitVars
    0.44
     MenuView
    0.43
     mecha
    0.43
    ########.
    0.43
     esternos
    0.43
     Airways
    0.42
    SP
    0.42
    Act Density 0.280%

    No Known Activations