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

    Neuronpedia

    INDEX
    Explanations

    trip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sele
    -0.08
    avel
    -0.07
    _IMPORTED
    -0.06
    ベル
    -0.06
    oueur
    -0.06
    _ll
    -0.06
     holog
    -0.06
    کور
    -0.06
     Sour
    -0.06
    aves
    -0.06
    POSITIVE LOGITS
     trip
    0.14
     Trip
    0.12
     trips
    0.10
    trip
    0.08
     citas
    0.08
    ep
    0.08
     recip
    0.08
     Freddie
    0.08
    lap
    0.07
     Lynn
    0.07
    Act Density 0.011%

    No Known Activations