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

    Neuronpedia

    INDEX
    Explanations

    -primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allocator
    -0.08
    (NS
    -0.07
     Selector
    -0.07
    ."),
    -0.07
    дал
    -0.07
    .games
    -0.06
    management
    -0.06
    -0.06
     coop
    -0.06
     marca
    -0.06
    POSITIVE LOGITS
     undergrad
    0.06
    ाष
    0.06
     अफ
    0.06
    EH
    0.06
    奉
    0.06
     Puppy
    0.06
     RIGHT
    0.06
    yıl
    0.06
    -yyyy
    0.06
    ию
    0.06
    Act Density 0.002%

    No Known Activations