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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نم
    -0.07
    XmlAttribute
    -0.07
    �
    -0.07
     Shemale
    -0.07
    也不想
    -0.07
    ")==
    -0.07
    อ
    -0.06
    亶
    -0.06
     النو
    -0.06
    ວ
    -0.06
    POSITIVE LOGITS
     tribes
    0.08
    绝对是
    0.07
    东部
    0.07
     Derek
    0.07
    .project
    0.07
     multitude
    0.07
    osopher
    0.07
    DP
    0.07
     통해서
    0.07
    ah
    0.06
    Act Density 0.005%

    No Known Activations