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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rows
    -0.07
     rehears
    -0.07
     From
    -0.07
     towel
    -0.06
     issued
    -0.06
     downs
    -0.06
    -hover
    -0.06
    pherd
    -0.06
    ří
    -0.06
    elements
    -0.06
    POSITIVE LOGITS
    ả
    0.08
    Có
    0.07
    :disable
    0.07
    uture
    0.06
    kos
    0.06
    PWM
    0.06
    Mur
    0.06
     muh
    0.06
    美元
    0.06
     melting
    0.06
    Act Density 0.475%

    No Known Activations