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

    Neuronpedia

    INDEX
    Explanations

    anthrop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чим
    -0.07
    .utf
    -0.07
    _IO
    -0.07
    .BAD
    -0.07
     ninja
    -0.06
     civilian
    -0.06
     назна
    -0.06
    .localtime
    -0.06
     peaceful
    -0.06
     Dean
    -0.06
    POSITIVE LOGITS
     anthrop
    0.10
    throp
    0.07
    rop
    0.07
     Anthrop
    0.07
     anthropology
    0.07
     Andersen
    0.07
     bodyParser
    0.06
    سه
    0.06
    strup
    0.06
     �
    0.06
    Act Density 0.003%

    No Known Activations