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

    Neuronpedia

    INDEX
    Explanations

    Lists and outlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reigning
    -0.08
    LOVE
    -0.08
     Glenn
    -0.08
     crow
    -0.08
     deth
    -0.08
    avn
    -0.07
     billions
    -0.07
    Joel
    -0.07
     tame
    -0.07
    ryd
    -0.07
    POSITIVE LOGITS
     ability
    0.12
     Ability
    0.11
     competency
    0.11
     proficiency
    0.10
     Fähigkeit
    0.10
     competencies
    0.10
    Ability
    0.10
     compétence
    0.10
     competence
    0.10
    掌
    0.10
    Act Density 0.027%

    No Known Activations