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

    Neuronpedia

    INDEX
    Explanations

    mathematical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itu
    -0.07
    �
    -0.07
     adher
    -0.06
    ї
    -0.06
    _quick
    -0.06
    атора
    -0.06
    的问题
    -0.06
     Fauc
    -0.06
    _mot
    -0.06
     interfer
    -0.06
    POSITIVE LOGITS
    ("***
    0.06
    _infos
    0.06
    قد
    0.06
    .Down
    0.06
    ALLENG
    0.06
    prompt
    0.06
    _travel
    0.06
    (Target
    0.06
    ACEMENT
    0.06
    }><
    0.06
    Act Density 0.057%

    No Known Activations