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

    Neuronpedia

    INDEX
    Explanations

    tokenizer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rand
    0.40
     rand
    0.39
    Rand
    0.38
     अधी
    0.37
     McMillan
    0.37
     improper
    0.36
     pathologic
    0.36
     computational
    0.35
    0.35
     explosive
    0.35
    POSITIVE LOGITS
     Oxidation
    0.38
    ayang
    0.36
    uch
    0.36
    avacanam
    0.35
    oyan
    0.35
    ieważ
    0.35
    ઐ
    0.35
    ream
    0.34
    ceau
    0.34
    issait
    0.34
    Act Density 0.000%

    No Known Activations