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

    Neuronpedia

    INDEX
    Explanations

    dandelions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    В
    -0.07
     В
    -0.07
    NSError
    -0.07
    К
    -0.07
    曾任
    -0.07
     Ver
    -0.06
    -0.06
    Failed
    -0.06
    放手
    -0.06
     his
    -0.06
    POSITIVE LOGITS
    Cha
    0.08
    เซล
    0.07
     EPA
    0.07
    thumbnails
    0.07
    脶
    0.07
    śl
    0.07
    的情况
    0.07
     bitch
    0.07
    <ll
    0.07
     luật
    0.06
    Act Density 0.000%

    No Known Activations