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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fashionable
    -0.06
    _it
    -0.06
    laví
    -0.06
     MIPS
    -0.06
     bicycles
    -0.06
     rear
    -0.06
     Radar
    -0.06
     l�
    -0.06
    ivan
    -0.05
     radius
    -0.05
    POSITIVE LOGITS
     lol
    0.07
     devel
    0.07
     "";↵
    0.06
    cook
    0.06
     Pare
    0.06
    alter
    0.06
     ↑
    0.06
    หาย
    0.06
     tir
    0.06
    .tif
    0.06
    Act Density 0.014%

    No Known Activations