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

    Neuronpedia

    INDEX
    Explanations

    Properties and options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mez
    -0.09
     consumir
    -0.09
     campeón
    -0.08
     consuming
    -0.08
     licking
    -0.08
     generar
    -0.08
    mless
    -0.08
     anim
    -0.08
     Bant
    -0.08
     lads
    -0.08
    POSITIVE LOGITS
     overrides
    0.09
    .additional
    0.09
    사항
    0.09
    เพิ่มเติม
    0.09
     influences
    0.08
     Overrides
    0.08
    extra
    0.08
     tweaks
    0.08
     influence
    0.08
     influencing
    0.08
    Act Density 0.009%

    No Known Activations