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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...'
    -0.07
    ţ
    -0.07
    ENUM
    -0.06
    たく
    -0.06
     hmm
    -0.06
     ever
    -0.06
    NSSet
    -0.06
     manus
    -0.06
    孙
    -0.06
    >(()
    -0.06
    POSITIVE LOGITS
    십시오
    0.07
     متوسط
    0.07
    (paths
    0.06
    IllegalAccessException
    0.06
    anical
    0.06
     diese
    0.06
    Ả
    0.06
    详
    0.06
     mage
    0.06
     平
    0.06
    Act Density 0.000%

    No Known Activations