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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    资格
    -0.08
     Thr
    -0.08
     qualifier
    -0.08
     属
    -0.08
     sociales
    -0.07
     perspectives
    -0.07
     NIC
    -0.07
     रु
    -0.07
     folders
    -0.07
     trunk
    -0.07
    POSITIVE LOGITS
     পাল
    0.09
     volley
    0.09
     provo
    0.08
     vomiting
    0.08
     së
    0.08
     હુમ
    0.08
     defensa
    0.08
     lament
    0.08
    USART
    0.08
    restore
    0.08
    Act Density 0.008%

    No Known Activations