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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GetName
    -0.07
     I
    -0.06
    Experiment
    -0.06
     Αυ
    -0.06
     ﾉ
    -0.06
     Defaults
    -0.06
     Escort
    -0.06
    Completion
    -0.06
     DIAG
    -0.06
     Indi
    -0.05
    POSITIVE LOGITS
     вз
    0.07
    ỹ
    0.07
    uforia
    0.07
    pray
    0.07
    ayla
    0.07
    razione
    0.07
    angent
    0.06
    .getLabel
    0.06
    agic
    0.06
    now
    0.06
    Act Density 0.386%

    No Known Activations