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

    Neuronpedia

    INDEX
    Explanations

    someone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tornado
    -0.08
    COM
    -0.07
    xF
    -0.07
    Increment
    -0.07
    give
    -0.07
    15
    -0.07
     Zheng
    -0.07
    929
    -0.06
     frustrating
    -0.06
     Evalu
    -0.06
    POSITIVE LOGITS
     synthesized
    0.07
     작업
    0.06
    »،
    0.06
    (yy
    0.06
     Sử
    0.06
    %%*/
    0.06
     offs
    0.06
     fetal
    0.06
     phổ
    0.06
    ecies
    0.06
    Act Density 0.007%

    No Known Activations