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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     in
    -0.07
    、と
    -0.07
    ичні
    -0.07
    御
    -0.06
    EndTime
    -0.06
    -i
    -0.06
     à
    -0.06
    antaged
    -0.06
     المر
    -0.06
    piel
    -0.06
    POSITIVE LOGITS
     but
    0.15
    but
    0.10
     BUT
    0.10
     however
    0.08
     yet
    0.08
    "But
    0.08
     But
    0.08
    -but
    0.08
     bec
    0.07
     hut
    0.07
    Act Density 0.062%

    No Known Activations