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

    Neuronpedia

    INDEX
    Explanations

    biographical profiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *l
    -0.07
    مف
    -0.07
    >"+↵
    -0.06
    뵨
    -0.06
    	user
    -0.06
    iant
    -0.06
    .getPlayer
    -0.06
     jal
    -0.06
    ➴
    -0.06
    inem
    -0.06
    POSITIVE LOGITS
     joints
    0.08
    舵
    0.07
     distant
    0.07
     shortest
    0.07
    棤
    0.07
    Depth
    0.06
     stiffness
    0.06
    干部职工
    0.06
    faker
    0.06
    .buf
    0.06
    Act Density 0.112%

    No Known Activations