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

    Neuronpedia

    INDEX
    Explanations

    hide the, match found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     зокрема
    0.41
     eventuali
    0.40
     molestias
    0.38
     économiques
    0.38
     среды
    0.37
    PRIMARY
    0.37
     aplicada
    0.36
    TELE
    0.36
    NSMakeRange
    0.36
    insect
    0.36
    POSITIVE LOGITS
     >=
    0.46
     father
    0.44
     certification
    0.37
     stands
    0.37
     XVI
    0.37
    FromServer
    0.37
     spontaneous
    0.36
     garant
    0.36
    扈
    0.36
     unsur
    0.36
    Act Density 0.000%

    No Known Activations