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

    Neuronpedia

    INDEX
    Explanations

    let's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     +
    0.79
     also
    0.70
     Tw
    0.66
     /
    0.66
     Ad
    0.64
     &
    0.64
     Delhi
    0.64
    0.64
     its
    0.63
     Di
    0.63
    POSITIVE LOGITS
    㕧
    0.85
    effectuer
    0.80
    iremos
    0.77
    ܤ
    0.77
     गिवन
    0.76
    Ꮘ
    0.76
     verilen
    0.75
    Ꮡ
    0.75
    ologici
    0.74
    ANSAS
    0.74
    Act Density 0.001%

    No Known Activations