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

    Neuronpedia

    INDEX
    Explanations

    lists and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ล
    0.43
     erklärte
    0.40
     alatt
    0.40
    REIB
    0.39
    ποι
    0.38
    Ρ
    0.38
    hola
    0.38
     unlikely
    0.37
    GN
    0.37
    Despite
    0.37
    POSITIVE LOGITS
     Oka
    0.50
     convection
    0.47
    ógicos
    0.47
     Loire
    0.46
     लेसन
    0.46
     Enfer
    0.46
     Joystick
    0.46
     seepage
    0.46
     normalization
    0.45
     Loy
    0.45
    Act Density 0.000%

    No Known Activations