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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ase
    -0.07
    аторы
    -0.06
    ajas
    -0.06
     mají
    -0.06
    _VAL
    -0.06
    .Re
    -0.06
     ministers
    -0.05
     станет
    -0.05
     эф
    -0.05
    mlin
    -0.05
    POSITIVE LOGITS
    .Open
    0.07
     horrend
    0.07
    VMLINUX
    0.07
     bits
    0.07
    acula
    0.07
    /Object
    0.06
     성
    0.06
     som
    0.06
    ุน
    0.06
    .sequence
    0.06
    Act Density 0.111%

    No Known Activations