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

    Neuronpedia

    INDEX
    Explanations

    information or opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teu
    0.44
     Archipelago
    0.41
     Communists
    0.40
    甾
    0.40
     Archbishop
    0.38
     returnMe
    0.38
     امر
    0.38
     phép
    0.37
     امرأة
    0.37
     ves
    0.37
    POSITIVE LOGITS
    sequently
    0.48
    rides
    0.45
    е
    0.43
    ਪਣ
    0.41
    BOR
    0.41
    phan
    0.40
    NCE
    0.40
    OCCO
    0.38
    tri
    0.38
    baden
    0.38
    Act Density 0.003%

    No Known Activations