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

    Neuronpedia

    INDEX
    Explanations

    Common English fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     цель
    -0.07
    tpl
    -0.07
     oversh
    -0.06
    SCALE
    -0.06
    osto
    -0.06
     timeline
    -0.06
    COMPARE
    -0.06
    啪
    -0.06
    URL
    -0.06
     lug
    -0.06
    POSITIVE LOGITS
    VE
    0.07
    .Scan
    0.06
    胶
    0.06
    Guardar
    0.06
     philosophers
    0.06
    gunta
    0.06
     vede
    0.06
    Sel
    0.06
    伸
    0.06
     Gins
    0.06
    Act Density 0.000%

    No Known Activations