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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sponge
    -0.07
     Pert
    -0.07
    .Cache
    -0.07
     smiled
    -0.07
    捋
    -0.07
     VX
    -0.07
     seventh
    -0.07
     skirt
    -0.06
     towering
    -0.06
     glitter
    -0.06
    POSITIVE LOGITS
    何
    0.08
     Before
    0.07
    https
    0.07
    ขณะ
    0.07
     oa
    0.06
     finances
    0.06
    @@
    0.06
    ทดลอง
    0.06
    onda
    0.06
    價格
    0.06
    Act Density 0.000%

    No Known Activations