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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thụ
    -0.07
     섬
    -0.06
    ในส
    -0.06
    /></
    -0.06
     diverted
    -0.06
    θη
    -0.06
     FRONT
    -0.06
     Levin
    -0.06
     Petit
    -0.06
     Kol
    -0.05
    POSITIVE LOGITS
    IGHLIGHT
    0.06
    ゼ
    0.06
    에
    0.06
    ####
    0.06
    VIS
    0.06
    ٥
    0.06
    .children
    0.06
    Dump
    0.06
    elerinden
    0.06
    prof
    0.06
    Act Density 0.051%

    No Known Activations