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

    Neuronpedia

    INDEX
    Explanations

    Ranting/Negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orz
    -0.06
    ‚ط
    -0.06
    .uri
    -0.06
    tos
    -0.06
    arrants
    -0.06
     Beitrag
    -0.06
     zvíř
    -0.06
     Tos
    -0.06
    Trace
    -0.06
    _gchandle
    -0.06
    POSITIVE LOGITS
     випадку
    0.06
    .IN
    0.06
    .first
    0.06
    extends
    0.06
    _DP
    0.06
     poised
    0.06
    �
    0.05
     cents
    0.05
    Emp
    0.05
     senza
    0.05
    Act Density 0.167%

    No Known Activations