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

    Neuronpedia

    INDEX
    Explanations

    Lake Tahoe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VisualStudio
    0.40
     principally
    0.38
     സോഷ്യ
    0.37
     Tolst
    0.36
     آئینے
    0.36
    alphabet
    0.36
    roit
    0.36
     алфа
    0.36
    廣場
    0.36
    securityMarks
    0.36
    POSITIVE LOGITS
     RI
    0.47
     LI
    0.44
     读取
    0.39
     wl
    0.39
    6
    0.38
    HE
    0.37
     MI
    0.37
    HAI
    0.37
     Interference
    0.37
    ε
    0.37
    Act Density 0.000%

    No Known Activations