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

    Neuronpedia

    INDEX
    Explanations

    assignment or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seq
    0.38
    ozer
    0.36
    ospitals
    0.36
    ష
    0.36
     esetén
    0.36
     Су
    0.36
     especiales
    0.36
     específicas
    0.36
    strate
    0.35
     ense
    0.35
    POSITIVE LOGITS
    鐒
    0.43
     dość
    0.39
     ;-
    0.36
    ClassObject
    0.36
    融
    0.36
     दुबे
    0.35
    Pent
    0.35
     penthouse
    0.35
    airo
    0.34
     citoyens
    0.34
    Act Density 0.000%

    No Known Activations