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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -loss
    -0.07
     wrote
    -0.07
     strives
    -0.07
     continues
    -0.07
     liar
    -0.07
     infusion
    -0.06
     regained
    -0.06
    AILS
    -0.06
    出售
    -0.06
    _git
    -0.06
    POSITIVE LOGITS
     rapport
    0.06
    FFE
    0.06
    814
    0.06
    	vm
    0.06
     rdf
    0.06
     αν
    0.06
    نگ
    0.06
    σιμοποι
    0.06
    ลล
    0.06
    鏡
    0.06
    Act Density 0.004%

    No Known Activations