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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
     Ре
    -0.07
    -month
    -0.07
     Merge
    -0.06
    ský
    -0.06
    72
    -0.06
     behaves
    -0.06
     entry
    -0.06
    URATION
    -0.06
    riculum
    -0.06
    POSITIVE LOGITS
     dispers
    0.06
    _MISS
    0.06
     отнош
    0.06
    (dateTime
    0.06
     confident
    0.06
    nem
    0.06
     ＿
    0.06
     unstoppable
    0.06
     acquaint
    0.06
    _stylesheet
    0.06
    Act Density 0.024%

    No Known Activations