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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ervice
    0.44
    層
    0.44
    對方
    0.40
    serde
    0.39
    رفة
    0.38
     層
    0.38
    0.38
     Census
    0.38
    Sally
    0.38
     reappear
    0.37
    POSITIVE LOGITS
     tubo
    0.42
     cụ
    0.39
     berd
    0.38
    लैंड
    0.37
    itats
    0.37
     cuanto
    0.36
     trasera
    0.36
    具体
    0.36
    nah
    0.36
     prid
    0.36
    Act Density 0.001%

    No Known Activations