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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uch
    -0.07
    .pc
    -0.07
    �
    -0.07
    cke
    -0.07
     specimen
    -0.07
     upp
    -0.07
    碰
    -0.07
    inkle
    -0.06
     perch
    -0.06
     Fargo
    -0.06
    POSITIVE LOGITS
    不满意
    0.07
    .syn
    0.07
    xFB
    0.07
    髋
    0.07
    十里
    0.07
    веща
    0.07
    对其真实
    0.07
    Queryable
    0.06
    `}↵
    0.06
    깞
    0.06
    Act Density 0.043%

    No Known Activations