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

    Neuronpedia

    INDEX
    Explanations

    Allegations of wrongdoing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whereby
    -0.07
    什么
    -0.06
     login
    -0.06
    似乎
    -0.06
    -0.06
    粉
    -0.06
    來
    -0.06
     ";↵
    -0.06
    .j
    -0.06
    _;↵↵
    -0.06
    POSITIVE LOGITS
    _rep
    0.07
     Anadolu
    0.07
     Fetish
    0.07
    Inicial
    0.06
    LAR
    0.06
    .AutoSize
    0.06
     mohl
    0.06
     DirectoryInfo
    0.06
     Poe
    0.06
     vais
    0.06
    Act Density 0.026%

    No Known Activations