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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
    Dataset
    -0.07
    facet
    -0.07
    895
    -0.07
     getIntent
    -0.07
    Sit
    -0.07
    .enterprise
    -0.06
     Güven
    -0.06
    297
    -0.06
     Collapse
    -0.06
    POSITIVE LOGITS
    alpha
    0.15
     Alpha
    0.14
     alpha
    0.14
     ALPHA
    0.11
    Alpha
    0.11
     α
    0.10
    -alpha
    0.10
    .Alpha
    0.10
    Leo
    0.09
     Alex
    0.09
    Act Density 0.016%

    No Known Activations