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

    Neuronpedia

    INDEX
    Explanations

    en dash

    np_max-act · gemini-2.0-flash

    specific names and titles related to governing positions or roles within various regions and countries.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     WARRANTY
    -0.07
    F
    -0.07
     Lap
    -0.07
    Name
    -0.06
    頭
    -0.06
    heads
    -0.06
     Tables
    -0.06
    _lvl
    -0.06
    xDE
    -0.06
    _EDGE
    -0.06
    POSITIVE LOGITS
     özelliği
    0.07
     prima
    0.06
    (__
    0.06
    (si
    0.06
    oslav
    0.06
    essoa
    0.06
     uint
    0.06
     jugador
    0.06
    ('$
    0.06
    (ps
    0.06
    Act Density 0.007%

    No Known Activations