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

    Neuronpedia

    INDEX
    Explanations

    Technical diagrams/specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    洗
    -0.07
     ongoing
    -0.07
    _OK
    -0.07
    协议
    -0.06
     finds
    -0.06
     Okay
    -0.06
     Else
    -0.06
     dvou
    -0.06
     mindset
    -0.06
    ה
    -0.06
    POSITIVE LOGITS
     environ
    0.07
     شامل
    0.07
    .getItems
    0.07
    일에
    0.07
    (Abstract
    0.07
     Crazy
    0.06
    地區
    0.06
     rgba
    0.06
    (question
    0.06
    getCode
    0.06
    Act Density 0.021%

    No Known Activations