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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oli
    -0.07
    蔓
    -0.07
     revenues
    -0.07
    Bru
    -0.07
    sport
    -0.07
     geek
    -0.07
    之事
    -0.07
    SingleNode
    -0.07
     vem
    -0.07
     volley
    -0.07
    POSITIVE LOGITS
    试剂
    0.07
     kilometers
    0.07
     taste
    0.07
    eter
    0.06
    -top
    0.06
    ллер
    0.06
    giene
    0.06
    чрежден
    0.06
     recognise
    0.06
     illness
    0.06
    Act Density 0.000%

    No Known Activations