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

    Neuronpedia

    INDEX
    Explanations

    code with integrity hashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDS
    -0.07
    ѡ
    -0.07
    cesso
    -0.07
    devices
    -0.07
    \xff
    -0.07
    🚵
    -0.07
     chaos
    -0.07
    uter
    -0.07
     kötü
    -0.07
     sickness
    -0.07
    POSITIVE LOGITS
    Base
    0.07
    _arg
    0.07
    .*↵↵
    0.07
     cowork
    0.07
     encoding
    0.07
     Hawaiian
    0.07
    过于
    0.07
     רא
    0.07
    类似的
    0.07
     shar
    0.07
    Act Density 0.000%

    No Known Activations