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

    Neuronpedia

    INDEX
    Explanations

    Hedging language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دم
    -0.08
    _ENCODE
    -0.07
     marine
    -0.07
    SharedPtr
    -0.07
    _EVAL
    -0.06
     取
    -0.06
     Mathematics
    -0.06
     creepy
    -0.06
     已
    -0.06
     underground
    -0.06
    POSITIVE LOGITS
     italic
    0.06
    ろう
    0.06
    .Here
    0.06
    …………
    0.06
    "".
    0.06
     kimse
    0.06
     Proposal
    0.06
    Groups
    0.06
    ULO
    0.06
     discussion
    0.06
    Act Density 0.178%

    No Known Activations