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

    Neuronpedia

    INDEX
    Explanations

    "ial" suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    υμ
    -0.07
     symlink
    -0.07
     Leap
    -0.07
     monastery
    -0.07
     Ro
    -0.07
    stanbul
    -0.07
    ดาห
    -0.06
    _pickle
    -0.06
     berth
    -0.06
     safeguards
    -0.06
    POSITIVE LOGITS
    .Action
    0.07
     '%"
    0.07
     action
    0.07
     fulfill
    0.07
    kal
    0.07
     evolving
    0.06
    val
    0.06
    142
    0.06
    alex
    0.06
     kepada
    0.06
    Act Density 0.001%

    No Known Activations