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

    Neuronpedia

    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sa
    -0.07
    487
    -0.06
    Return
    -0.06
    ρι
    -0.06
     τόσο
    -0.06
     Anonymous
    -0.06
     Return
    -0.06
     якої
    -0.06
    ②
    -0.06
    .age
    -0.06
    POSITIVE LOGITS
     wt
    0.12
     roofing
    0.10
     ctypes
    0.09
    extField
    0.07
     Supports
    0.07
    OC
    0.07
    ellation
    0.07
     recht
    0.07
    zing
    0.07
     Kent
    0.07
    Act Density 0.002%

    No Known Activations