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

    Neuronpedia

    INDEX
    Explanations

    sentiment and confidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ImVec
    -0.07
    仕
    -0.07
    kke
    -0.07
     eerste
    -0.06
     trying
    -0.06
    Immutable
    -0.06
    Callable
    -0.06
     sedm
    -0.06
     --------
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     parad
    0.06
     tonight
    0.06
    preh
    0.06
     sentiment
    0.06
    �
    0.06
    ujet
    0.06
     recept
    0.06
    /routes
    0.06
     Sam
    0.06
    blers
    0.06
    Act Density 0.018%

    No Known Activations