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

    Neuronpedia

    INDEX
    Explanations

    descriptions/profiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     przed
    -0.07
    .square
    -0.07
    (depth
    -0.07
     cervical
    -0.07
    니스
    -0.07
     screenshot
    -0.07
     manpower
    -0.07
    如何
    -0.07
     vergi
    -0.06
     hep
    -0.06
    POSITIVE LOGITS
    "};↵
    0.06
     discourage
    0.06
     EURO
    0.06
    adiens
    0.06
     totaled
    0.06
    URT
    0.06
    ===============↵
    0.06
    oseconds
    0.05
    ."),↵
    0.05
    .visitInsn
    0.05
    Act Density 0.022%

    No Known Activations