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

    Neuronpedia

    INDEX
    Explanations

    single-digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     актив
    -0.07
    _FALL
    -0.07
     Sanity
    -0.07
     dri
    -0.07
     Sở
    -0.07
     LAB
    -0.07
    Tony
    -0.07
     gam
    -0.07
     hvor
    -0.06
     osp
    -0.06
    POSITIVE LOGITS
    محك
    0.07
    官网
    0.07
    נחש
    0.07
    뒈
    0.06
     rebuilt
    0.06
    붕
    0.06
     readdir
    0.06
    כם
    0.06
    묀
    0.06
     CallingConvention
    0.06
    Act Density 0.005%

    No Known Activations