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

    Neuronpedia

    INDEX
    Explanations

    unlock new, allow yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    0.63
    HEN
    0.50
    hen
    0.49
     efectivamente
    0.49
    em
    0.48
    Fs
    0.48
    WORTH
    0.47
     memahami
    0.47
    kami
    0.46
    KEL
    0.46
    POSITIVE LOGITS
     batt
    0.47
     Civic
    0.42
    霹
    0.41
     DCs
    0.39
     dwellers
    0.39
    Link
    0.39
     fitness
    0.39
     बिज
    0.39
    дить
    0.39
     wellness
    0.38
    Act Density 0.001%

    No Known Activations