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

    Neuronpedia

    INDEX
    Explanations

    Malware/security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [$_
    -0.06
     RVA
    -0.06
    sprites
    -0.06
     площад
    -0.06
     relu
    -0.06
    tgt
    -0.06
     Мініст
    -0.06
    같
    -0.06
    netinet
    -0.06
    徐
    -0.06
    POSITIVE LOGITS
    孔
    0.06
    Group
    0.06
    Tasks
    0.06
    isu
    0.06
     phases
    0.06
    िवर
    0.06
    .isPlaying
    0.06
     stands
    0.06
     subscript
    0.06
    cut
    0.06
    Act Density 0.450%

    No Known Activations