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

    Neuronpedia

    INDEX
    Explanations

    CSS transform translateY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.70
    ik
    1.56
    an
    1.54
    op
    1.51
    ate
    1.45
    oc
    1.38
    é
    1.38
    ia
    1.37
    ā
    1.35
    ad
    1.34
    POSITIVE LOGITS
    1.26
    daki
    1.18
     Akademii
    1.17
     littoral
    1.16
     Pago
    1.14
     April
    1.13
     vidro
    1.13
     rtl
    1.12
     olmay
    1.11
     totality
    1.11
    Act Density 0.055%

    No Known Activations