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

    Neuronpedia

    INDEX
    Explanations

    words or phrases connecting multiple concepts

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     africain
    -0.64
     myſelf
    -0.63
     vägen
    -0.58
     vallée
    -0.57
     poupée
    -0.54
     soeur
    -0.53
     africaine
    -0.53
     pauv
    -0.52
     purpoſe
    -0.52
    sper
    -0.52
    POSITIVE LOGITS
     lenker
    0.76
    }());
    0.57
    HasAnnotation
    0.56
    Архівовано
    0.54
    "}")
    0.52
    ()]);
    0.51
    ={}
    0.50
    })();
    0.48
     ivelany
    0.47
     <<<<<<<<<<<<<<
    0.47
    Act Density 0.864%

    No Known Activations