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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ση
    -0.06
     оч
    -0.06
     neighbours
    -0.06
    หาย
    -0.06
    ापन
    -0.06
    963
    -0.06
     Cous
    -0.06
    adem
    -0.06
    zers
    -0.06
    woods
    -0.06
    POSITIVE LOGITS
     gi
    0.08
     اساس
    0.07
    -based
    0.07
     diret
    0.07
     based
    0.07
     markedly
    0.06
     Perform
    0.06
    -economic
    0.06
     Deliver
    0.06
    _miss
    0.06
    Act Density 0.168%

    No Known Activations