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

    Neuronpedia

    INDEX
    Explanations

    equality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MI
    -0.08
     ребен
    -0.07
    .messaging
    -0.07
    فهم
    -0.07
     reconstructed
    -0.07
    เสนอ
    -0.07
     musica
    -0.07
    	me
    -0.06
     New
    -0.06
    .dataGridView
    -0.06
    POSITIVE LOGITS
     Cary
    0.07
    .pad
    0.07
    {j
    0.07
    _prim
    0.06
    Erro
    0.06
    샀
    0.06
    ลงทะ
    0.06
     refusal
    0.06
    빳
    0.06
    镶
    0.06
    Act Density 0.015%

    No Known Activations