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

    Neuronpedia

    INDEX
    Explanations

    .CodeAnalysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     závis
    -0.06
     příslu
    -0.06
    .ib
    -0.06
    -inst
    -0.06
    �
    -0.06
    司
    -0.06
    อบ
    -0.06
    idea
    -0.06
    222
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     excuse
    0.08
    .CodeAnalysis
    0.08
     WITHOUT
    0.07
     backlash
    0.07
     showdown
    0.07
     rewarded
    0.07
     групи
    0.06
    ь
    0.06
     CLOSE
    0.06
     ONLY
    0.06
    Act Density 0.000%

    No Known Activations