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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compiling
    -0.08
    omore
    -0.07
     propelled
    -0.07
    (Spring
    -0.07
    rello
    -0.07
     mistaken
    -0.07
     Buffalo
    -0.07
    Número
    -0.07
     belum
    -0.07
     welded
    -0.07
    POSITIVE LOGITS
     T
    0.07
    Object
    0.07
    Interestingly
    0.07
    ┑
    0.07
    avage
    0.07
    흡
    0.07
     מור
    0.06
     []↵↵↵
    0.06
    Modification
    0.06
    _bits
    0.06
    Act Density 0.075%

    No Known Activations