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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tracking
    -0.06
     Soldier
    -0.06
     crises
    -0.06
     climates
    -0.06
     Williams
    -0.06
    ��
    -0.06
     loro
    -0.06
    atk
    -0.06
     acted
    -0.06
     crane
    -0.06
    POSITIVE LOGITS
     skipping
    0.07
    manifest
    0.07
    aciones
    0.07
     pag
    0.07
     skipped
    0.07
    .tex
    0.06
    نسان
    0.06
    -remove
    0.06
     skip
    0.06
     declar
    0.06
    Act Density 0.045%

    No Known Activations