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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emos
    -0.07
    _DEN
    -0.07
    _KEYS
    -0.06
    dictions
    -0.06
    ayload
    -0.06
     ade
    -0.06
     Contrast
    -0.06
     Bes
    -0.06
     Whats
    -0.06
     тисяч
    -0.06
    POSITIVE LOGITS
     PCA
    0.07
    rrha
    0.07
    posable
    0.06
    532
    0.06
     yahoo
    0.06
    "}↵
    0.06
    urrence
    0.06
     UITextView
    0.06
     NSRange
    0.06
    SHIP
    0.06
    Act Density 0.000%

    No Known Activations