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

    Neuronpedia

    INDEX
    Explanations

    the question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ultimate
    0.76
    Ultimate
    0.69
     Ultimate
    0.67
    ultimate
    0.63
     sempurna
    0.47
    究
    0.43
    "]):
    0.42
     ideale
    0.41
    ERS
    0.41
     ultim
    0.41
    POSITIVE LOGITS
     séquence
    0.46
    సం
    0.46
     과정
    0.42
    >}
    0.39
     pouls
    0.37
     moods
    0.37
     angular
    0.37
     जवाहर
    0.36
     mysqli
    0.36
     éves
    0.36
    Act Density 0.017%

    No Known Activations