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

    Neuronpedia

    INDEX
    Explanations

    phrases of similarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اگر
    0.38
     extrémités
    0.38
     durs
    0.38
     oiseaux
    0.38
    ÈRE
    0.37
     kebanyakan
    0.36
     assertFalse
    0.36
    ’
    0.36
     भले
    0.35
     après
    0.35
    POSITIVE LOGITS
    provides
    0.61
    Provides
    0.55
     Provides
    0.52
    featuring
    0.50
    provide
    0.49
    including
    0.45
    untuk
    0.44
    Provide
    0.44
    an
    0.43
     Provide
    0.42
    Act Density 0.377%

    No Known Activations