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

    Neuronpedia

    INDEX
    Explanations

    contracts and agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '=
    -0.07
    /'↵
    -0.07
    '↵//
    -0.07
    �
    -0.07
     feedback
    -0.07
    ARG
    -0.07
     '↵
    -0.07
     aesthetics
    -0.06
     phenomenon
    -0.06
    换
    -0.06
    POSITIVE LOGITS
     Ready
    0.14
     preparedness
    0.14
     ready
    0.13
     запас
    0.13
     readiness
    0.12
     Bereits
    0.12
     poised
    0.12
     מראש
    0.12
     готовы
    0.12
    备用
    0.11
    Act Density 0.100%

    No Known Activations