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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Klaus
    -0.08
    “These
    -0.08
    แบร
    -0.07
    💢
    -0.07
    尼斯
    -0.07
    strap
    -0.07
    asp
    -0.07
     paris
    -0.07
    😒
    -0.07
     ASM
    -0.07
    POSITIVE LOGITS
    Observ
    0.08
    𖥨
    0.07
     restrict
    0.07
     المتعل
    0.07
     centrif
    0.07
    ﻗ
    0.07
    申し込み
    0.07
    cy
    0.07
    outing
    0.06
     التق
    0.06
    Act Density 0.001%

    No Known Activations