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

    Neuronpedia

    INDEX
    Explanations

    humans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assistance
    -0.07
    ندية
    -0.07
    Split
    -0.07
     organise
    -0.07
    "After
    -0.07
     зрост
    -0.07
    Contrib
    -0.07
     заходів
    -0.06
    kj
    -0.06
    blick
    -0.06
    POSITIVE LOGITS
     humans
    0.15
     Humans
    0.12
    Humans
    0.08
    GRES
    0.07
    wjgl
    0.07
     Us
    0.07
     chambers
    0.06
     drone
    0.06
    nea
    0.06
     HTTPS
    0.06
    Act Density 0.011%

    No Known Activations