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

    Neuronpedia

    INDEX
    Explanations

    numerical codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stra
    -0.07
     establishes
    -0.07
     yup
    -0.07
     celebrity
    -0.06
     MethodInfo
    -0.06
    (["
    -0.06
     Karl
    -0.06
     Lith
    -0.06
     SVN
    -0.06
    '^
    -0.06
    POSITIVE LOGITS
     alcan
    0.08
    231
    0.07
    _EVENTS
    0.07
    uti
    0.07
     scri
    0.07
    unctuation
    0.07
     privile
    0.07
     //
↵
    0.07
    unun
    0.06
    INARY
    0.06
    Act Density 0.005%

    No Known Activations