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

    Neuronpedia

    INDEX
    Explanations

    Scientific/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﻮ
    -0.06
    .DataType
    -0.06
     subst
    -0.06
     raging
    -0.06
     grilled
    -0.06
    +E
    -0.06
    。在
    -0.06
    移到
    -0.06
    在地
    -0.05
     scratches
    -0.05
    POSITIVE LOGITS
     Classe
    0.07
    irez
    0.07
    ialias
    0.07
     JACK
    0.07
     slogan
    0.06
     physically
    0.06
     cryptographic
    0.06
     intimidating
    0.06
    -properties
    0.06
     methodName
    0.06
    Act Density 0.092%

    No Known Activations