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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لمات
    -0.07
     首页
    -0.06
     reluctance
    -0.06
     Isaiah
    -0.06
     Bewert
    -0.06
    Port
    -0.06
     Administrator
    -0.06
    .NewReader
    -0.06
    _PARAMETERS
    -0.06
     Malta
    -0.06
    POSITIVE LOGITS
    _CL
    0.07
     catching
    0.06
     todos
    0.06
     phenomen
    0.06
    keletal
    0.06
    �
    0.06
    AML
    0.06
    .deepcopy
    0.06
    _VALUE
    0.06
     purpose
    0.06
    Act Density 0.016%

    No Known Activations