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

    Neuronpedia

    INDEX
    Explanations

    start of document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patrol
    -0.09
    .Def
    -0.07
    ondon
    -0.07
    wait
    -0.07
    Grace
    -0.07
    yoruz
    -0.07
     resistencia
    -0.06
     ciudad
    -0.06
    may
    -0.06
     vill
    -0.06
    POSITIVE LOGITS
     subsequent
    0.13
     repercussions
    0.12
     Subse
    0.12
     subsequently
    0.12
     ramifications
    0.12
     conséquences
    0.11
     casc
    0.11
     downstream
    0.11
     Cascade
    0.11
     Subsequently
    0.11
    Act Density 0.175%

    No Known Activations