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

    Neuronpedia

    INDEX
    Explanations

    professional work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    也算是
    -0.07
    俄罗斯
    -0.07
     incest
    -0.07
    갸
    -0.07
    תוספת
    -0.07
    蠓
    -0.07
     rallies
    -0.07
    anticipated
    -0.06
    亚军
    -0.06
    珸
    -0.06
    POSITIVE LOGITS
    Mock
    0.07
     Occupation
    0.07
     continuous
    0.07
    ⽥
    0.07
    rk
    0.06
     badge
    0.06
    policy
    0.06
    Large
    0.06
     ED
    0.06
    _WR
    0.06
    Act Density 0.150%

    No Known Activations