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

    Neuronpedia

    INDEX
    Explanations

    gases and exhaust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pat
    0.46
    ensitive
    0.45
    Legacy
    0.45
    Chairman
    0.43
     sensitivity
    0.43
    Que
    0.42
     Chairman
    0.42
    man
    0.42
    Y
    0.42
     contribution
    0.41
    POSITIVE LOGITS
    ólicos
    0.54
     europeos
    0.53
    치의
    0.51
     범위
    0.50
    도의
    0.49
     monstru
    0.49
     triángulos
    0.48
    loadNpm
    0.48
     pedibus
    0.47
    대의
    0.47
    Act Density 0.000%

    No Known Activations