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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counting
    -0.07
     ark
    -0.07
     immortal
    -0.06
     mix
    -0.06
     clusters
    -0.06
     descriptors
    -0.06
     Saved
    -0.06
     Helpers
    -0.06
     потен
    -0.06
     wrote
    -0.06
    POSITIVE LOGITS
     ná
    0.06
     Intercept
    0.06
    0.06
    ';
↵
    0.06
    �
    0.06
    "encoding
    0.06
    _Level
    0.06
     kültür
    0.06
    ~↵↵
    0.06
    	mv
    0.06
    Act Density 0.011%

    No Known Activations