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

    Neuronpedia

    INDEX
    Explanations

    Samsung SSD models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surviv
    0.51
     operas
    0.49
     RoHS
    0.47
    豢
    0.47
     Levin
    0.46
     prostit
    0.46
     Leibn
    0.46
     Lollipop
    0.45
    🌭
    0.45
     gingham
    0.44
    POSITIVE LOGITS
    ma
    0.63
    n
    0.48
    cv
    0.46
    pt
    0.45
    ма
    0.45
    nur
    0.45
    se
    0.44
    к
    0.44
    src
    0.43
    ın
    0.43
    Act Density 0.002%

    No Known Activations