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

    Neuronpedia

    INDEX
    Explanations

    level set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    г
    0.12
    essi
    0.11
    een
    0.11
    P
    0.11
    B
    0.11
     possesses
    0.11
    question
    0.11
    issy
    0.10
    M
    0.10
    irmed
    0.10
    POSITIVE LOGITS
     impianti
    0.11
     například
    0.11
    Proofs
    0.11
    耐
    0.11
    壁
    0.11
    🏛
    0.11
     impi
    0.11
     bună
    0.11
    狛
    0.11
     microarray
    0.11
    Act Density 0.001%

    No Known Activations