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

    Neuronpedia

    INDEX
    Explanations

    sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hät
    -0.08
     כד
    -0.07
    �
    -0.07
     đứ
    -0.06
     utmost
    -0.06
    ſt
    -0.06
     loaders
    -0.06
     Download
    -0.06
    บรร
    -0.06
    	grid
    -0.06
    POSITIVE LOGITS
    .safe
    0.08
    _Generic
    0.08
    会被
    0.08
    ARY
    0.07
    は
    0.07
     barrier
    0.07
     Canon
    0.07
    Incomplete
    0.07
     modifier
    0.07
    偏离
    0.07
    Act Density 0.030%

    No Known Activations