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

    Neuronpedia

    INDEX
    Explanations

    Countertop materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ein
    -0.08
     touted
    -0.07
    massage
    -0.07
    ]-'
    -0.07
    让人
    -0.07
     "").
    -0.07
    _digit
    -0.07
    .connector
    -0.07
    ())))↵
    -0.07
    \P
    -0.07
    POSITIVE LOGITS
     Bryan
    0.07
    美方
    0.07
     Needle
    0.07
    蜜蜂
    0.07
    ള
    0.06
    昴
    0.06
     advant
    0.06
     obra
    0.06
    _WALL
    0.06
    [channel
    0.06
    Act Density 0.016%

    No Known Activations