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

    Neuronpedia

    INDEX
    Explanations

    transfer learning/generalization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cabins
    -0.07
     weak
    -0.07
     banging
    -0.07
     kino
    -0.06
     Mold
    -0.06
    itives
    -0.06
    ada
    -0.06
    だって
    -0.06
     consulate
    -0.06
     blas
    -0.06
    POSITIVE LOGITS
    ClassLoader
    0.07
     AtomicInteger
    0.07
    ;"><?
    0.07
     sequ
    0.06
    θερ
    0.06
     окра
    0.06
    vince
    0.06
     hát
    0.06
    魔法
    0.06
     Devlet
    0.06
    Act Density 0.022%

    No Known Activations