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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    іг
    -0.06
     Advertising
    -0.06
    byt
    -0.06
     Connect
    -0.06
     frosting
    -0.06
    idth
    -0.06
     East
    -0.06
    sville
    -0.06
     itching
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     PI
    0.07
    tf
    0.07
     TAM
    0.07
    OFFSET
    0.07
    prof
    0.07
     sequ
    0.07
     SEEK
    0.07
     спож
    0.06
    swing
    0.06
    TF
    0.06
    Act Density 0.003%

    No Known Activations