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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     последние
    -0.09
    就像
    -0.07
     retrieved
    -0.07
    PathComponent
    -0.07
    最低
    -0.07
    九江
    -0.07
    LastError
    -0.07
    .separator
    -0.07
    奶奶
    -0.07
    lyph
    -0.07
    POSITIVE LOGITS
    ᴋ
    0.07
     //////////
    0.07
    sess
    0.07
     �
    0.07
     solely
    0.07
    技
    0.06
    ]"↵
    0.06
    aks
    0.06
    may
    0.06
    عمال
    0.06
    Act Density 0.001%

    No Known Activations