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

    Neuronpedia

    INDEX
    Explanations

    Chinese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forgot
    -0.09
     equations
    -0.09
     perdeu
    -0.08
     진행
    -0.08
     perder
    -0.08
     einde
    -0.07
    骗局
    -0.07
     Casinos
    -0.07
    argo
    -0.07
     Sentinel
    -0.07
    POSITIVE LOGITS
     aptitude
    0.13
     mindset
    0.13
     способность
    0.12
    Ability
    0.11
     ability
    0.11
     awareness
    0.11
    能力
    0.11
     способности
    0.11
     instincts
    0.11
     posture
    0.11
    Act Density 0.029%

    No Known Activations