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

    Neuronpedia

    INDEX
    Explanations

    true

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egers
    -0.07
    节
    -0.07
     kayb
    -0.06
     -=
    -0.06
    oles
    -0.06
     bazen
    -0.06
     bins
    -0.06
    VectorXd
    -0.06
    boBox
    -0.06
     gap
    -0.06
    POSITIVE LOGITS
     true
    0.10
     truly
    0.09
    true
    0.09
     True
    0.09
    True
    0.09
    _True
    0.09
    1
    0.08
     Turkish
    0.08
    .turn
    0.08
     Up
    0.08
    Act Density 0.040%

    No Known Activations