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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expiration
    -0.08
    れない
    -0.07
     transformations
    -0.07
     encryption
    -0.07
     dispersion
    -0.06
     cosine
    -0.06
     hurting
    -0.06
    Compilation
    -0.06
     quartz
    -0.06
    ipel
    -0.06
    POSITIVE LOGITS
    theon
    0.08
    `,`
    0.08
    și
    0.07
    .Statement
    0.07
    .story
    0.07
    głos
    0.07
    唏
    0.07
     hastily
    0.06
    增值服务
    0.06
    神经系统
    0.06
    Act Density 0.003%

    No Known Activations