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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -------------</
    -0.07
    천
    -0.07
    цер
    -0.07
    赢
    -0.07
     Suzuki
    -0.06
     Ihnen
    -0.06
    boru
    -0.06
    isease
    -0.06
    işi
    -0.06
     भव
    -0.06
    POSITIVE LOGITS
     displacement
    0.07
     Config
    0.07
    _fault
    0.06
    "=>"
    0.06
    .filters
    0.06
    ;a
    0.06
    +i
    0.06
     hostages
    0.06
    _Color
    0.06
     displ
    0.06
    Act Density 0.514%

    No Known Activations