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

    Neuronpedia

    INDEX
    Explanations

    clear plastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    韪
    0.40
    ೃಷ್ಣ
    0.39
    🤸
    0.39
    र्ण
    0.38
     공부
    0.37
    ับสนุน
    0.37
    परेट
    0.37
     vanishes
    0.37
    Checksum
    0.37
     Zeich
    0.37
    POSITIVE LOGITS
    iterator
    0.40
    substring
    0.39
    dictionary
    0.39
    ంజ
    0.37
    ferm
    0.37
    threshold
    0.37
    iter
    0.36
     নব
    0.36
     সবসময়
    0.35
    agnie
    0.35
    Act Density 0.000%

    No Known Activations