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

    Neuronpedia

    INDEX
    Explanations

    actuators and motors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _xt
    -0.07
     medicine
    -0.07
     dermat
    -0.07
    ryptography
    -0.07
     checker
    -0.07
     vagina
    -0.07
     commentary
    -0.07
     Media
    -0.07
    click
    -0.07
    esian
    -0.07
    POSITIVE LOGITS
     lean
    0.08
    纾
    0.08
    ವ
    0.07
    来回
    0.07
    bound
    0.07
    目標
    0.07
    谅解
    0.07
    .running
    0.07
    渑
    0.07
    👊
    0.06
    Act Density 0.040%

    No Known Activations