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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oversees
    -0.06
     Criteria
    -0.06
     misog
    -0.06
     Constraint
    -0.06
    _CA
    -0.06
     Kee
    -0.06
    =<?=
    -0.06
     plentiful
    -0.06
    -st
    -0.06
     подум
    -0.06
    POSITIVE LOGITS
    webs
    0.07
    ้าน
    0.07
     FF
    0.06
    にある
    0.06
    [assembly
    0.06
    واع
    0.06
    "]/
    0.06
    0.06
    τού
    0.06
    '><
    0.06
    Act Density 0.009%

    No Known Activations