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

    Neuronpedia

    INDEX
    Explanations

    `

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    marshall
    -0.07
     broadcasts
    -0.07
     speakers
    -0.07
     certification
    -0.07
     collaborated
    -0.06
    odi
    -0.06
    CD
    -0.06
    CE
    -0.06
    чів
    -0.06
    anova
    -0.06
    POSITIVE LOGITS
    两人
    0.07
     деятель
    0.06
    监听
    0.06
     Starter
    0.06
     cmake
    0.06
    .setHorizontalGroup
    0.06
     forfe
    0.06
    mat
    0.06
    ाजप
    0.06
     خودش
    0.06
    Act Density 0.031%

    No Known Activations