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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⚟
    -0.07
     pops
    -0.07
     transmit
    -0.06
     motivational
    -0.06
     suprem
    -0.06
     leans
    -0.06
     idea
    -0.06
     philanth
    -0.06
    roc
    -0.06
     infer
    -0.06
    POSITIVE LOGITS
     brother
    0.07
    cimal
    0.07
    ']."
    0.07
    ...)
    0.07
    @NoArgsConstructor
    0.07
    毒性
    0.07
    瓷器
    0.07
    𝐍
    0.07
     بتاريخ
    0.06
    building
    0.06
    Act Density 0.002%

    No Known Activations