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

    Neuronpedia

    INDEX
    Explanations

    little bit of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     форм
    0.39
     मिलना
    0.38
     экономической
    0.37
     temprano
    0.36
     школи
    0.35
     экономики
    0.35
     engend
    0.35
     война
    0.35
    Educ
    0.35
     школа
    0.35
    POSITIVE LOGITS
     lowering
    0.42
     přid
    0.39
     scallops
    0.39
     scallop
    0.39
     finish
    0.39
     gravity
    0.39
     scarf
    0.38
     adds
    0.38
     add
    0.38
     spice
    0.38
    Act Density 0.000%

    No Known Activations