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

    Neuronpedia

    INDEX
    Explanations

    actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fixes
    0.39
     deals
    0.39
    áp
    0.38
    deals
    0.38
    alg
    0.38
    Charts
    0.37
     alg
    0.37
    Ind
    0.37
     záv
    0.37
     Approaches
    0.37
    POSITIVE LOGITS
    舉行
    0.39
     read
    0.39
    妨
    0.36
     trasferimento
    0.36
     വായി
    0.36
     Walpole
    0.36
     march
    0.35
    ሀ
    0.35
    arness
    0.35
     MediaQuery
    0.35
    Act Density 0.000%

    No Known Activations