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

    Neuronpedia

    INDEX
    Explanations

    Personal anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ({"
    -0.07
     Tyto
    -0.07
     �
    -0.07
     "_
    -0.07
     Ca
    -0.07
     판
    -0.06
    	float
    -0.06
     سطح
    -0.06
     cảm
    -0.06
    ."\
    -0.06
    POSITIVE LOGITS
    णन
    0.07
     behalf
    0.07
    andan
    0.07
    ж
    0.07
     dream
    0.06
    composer
    0.06
    Fly
    0.06
    aces
    0.06
    imations
    0.06
     çalışma
    0.06
    Act Density 0.007%

    No Known Activations