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

    Neuronpedia

    INDEX
    Explanations

    Newlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुभव
    -0.07
    pol
    -0.06
    unset
    -0.06
     FP
    -0.06
     wards
    -0.06
     Ελλην
    -0.06
     rev
    -0.06
    sen
    -0.06
     Tent
    -0.05
     wreck
    -0.05
    POSITIVE LOGITS
     MSI
    0.07
     prostitu
    0.07
    _MISC
    0.07
    KeyValue
    0.06
    管理员
    0.06
     Doctrine
    0.06
    (stream
    0.06
    Syntax
    0.06
    threshold
    0.06
    UTDOWN
    0.06
    Act Density 0.001%

    No Known Activations