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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impeccable
    -0.08
    Sal
    -0.07
     deja
    -0.07
     Gorgeous
    -0.06
    97
    -0.06
    nitř
    -0.06
     πιο
    -0.06
    Cog
    -0.06
    Islam
    -0.06
    CLOSE
    -0.06
    POSITIVE LOGITS
     ns
    0.07
    _face
    0.07
     dobr
    0.06
     grate
    0.06
    ns
    0.06
     truth
    0.06
    ngth
    0.06
    adc
    0.06
    /edit
    0.06
    vous
    0.06
    Act Density 0.425%

    No Known Activations