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

    Neuronpedia

    INDEX
    Explanations

    thesis, sample, objective, title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Incluso
    0.43
    绰
    0.42
     previstas
    0.40
     сум
    0.39
    洧
    0.39
    buried
    0.38
    coords
    0.38
     attentes
    0.38
     cuadrado
    0.37
     aventuras
    0.37
    POSITIVE LOGITS
     Sample
    0.57
     sample
    0.57
    Sample
    0.57
     SAMPLE
    0.56
    sample
    0.55
    Writing
    0.54
    Developing
    0.53
     example
    0.52
     Writing
    0.52
     Developing
    0.51
    Act Density 0.000%

    No Known Activations