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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ко
    -0.07
     dazzling
    -0.06
     рабо
    -0.06
    Global
    -0.06
     Minecraft
    -0.06
    asca
    -0.06
    們
    -0.06
     sequencing
    -0.06
    させ
    -0.06
     visually
    -0.06
    POSITIVE LOGITS
    .Inter
    0.08
     motorcycle
    0.07
     hire
    0.07
    注
    0.06
    .Models
    0.06
     aside
    0.06
    942
    0.06
     hires
    0.06
     WR
    0.06
    ened
    0.06
    Act Density 0.000%

    No Known Activations