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

    Neuronpedia

    INDEX
    Explanations

    developer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invariant
    -0.08
    ibo
    -0.07
     мам
    -0.07
     Vũ
    -0.07
    胜利
    -0.06
    即将
    -0.06
     anth
    -0.06
    Qui
    -0.06
    Mon
    -0.06
     Joan
    -0.06
    POSITIVE LOGITS
    CppGuid
    0.07
    ("↵
    0.07
     cellForRowAt
    0.07
    킁
    0.07
    _cores
    0.07
    竑
    0.07
    _MEM
    0.07
    ifferent
    0.07
    FormatException
    0.06
    _was
    0.06
    Act Density 0.014%

    No Known Activations