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

    Neuronpedia

    INDEX
    Explanations

    object

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ดาว
    -0.07
     Buffered
    -0.06
    ژی
    -0.06
     Sto
    -0.06
     Caesar
    -0.06
    spa
    -0.06
    vely
    -0.06
     raw
    -0.06
     anger
    -0.06
     darkness
    -0.06
    POSITIVE LOGITS
     verdiği
    0.07
     AuthenticationService
    0.07
    #####↵
    0.07
    ++;
↵
↵
    0.07
    _trigger
    0.07
    ﻠ
    0.07
    .selectAll
    0.06
     amacı
    0.06
     jealousy
    0.06
     ransom
    0.06
    Act Density 0.025%

    No Known Activations