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

    Neuronpedia

    INDEX
    Explanations

    stress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uniform
    -0.07
    _ng
    -0.07
    𬸣
    -0.07
    枇
    -0.07
     hoax
    -0.07
     Plum
    -0.06
     Box
    -0.06
    ✂
    -0.06
     pockets
    -0.06
     blossom
    -0.06
    POSITIVE LOGITS
     stress
    0.09
     stresses
    0.08
    (profile
    0.07
    应力
    0.07
    "];
    0.07
    ietf
    0.07
    圣
    0.07
    0.07
    Past
    0.07
    压力
    0.07
    Act Density 0.011%

    No Known Activations