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

    Neuronpedia

    INDEX
    Explanations

    β

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    whereIn
    -0.07
    FEATURE
    -0.07
     Luc
    -0.07
    _tC
    -0.06
    '↵↵
    -0.06
    라마
    -0.06
    jandro
    -0.06
     أث
    -0.06
     παιδ
    -0.06
    亚洲
    -0.06
    POSITIVE LOGITS
     preceded
    0.07
     separate
    0.07
     weld
    0.06
     از
    0.06
    还
    0.06
    üzel
    0.06
    _particle
    0.06
    вести
    0.06
     constituents
    0.06
     diệt
    0.06
    Act Density 0.001%

    No Known Activations