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

    Neuronpedia

    INDEX
    Explanations

    die

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     accompagn
    -0.07
     quadr
    -0.07
    phant
    -0.07
    uv
    -0.06
     certificates
    -0.06
    -0.06
     companion
    -0.06
     Verb
    -0.06
    -0.06
    POSITIVE LOGITS
     Die
    0.17
     die
    0.15
    Die
    0.14
     DIE
    0.13
    die
    0.12
     Dies
    0.12
     dies
    0.11
     Das
    0.09
     tire
    0.08
    из
    0.08
    Act Density 0.010%

    No Known Activations