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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rsp
    -0.07
    的认可
    -0.07
     наб
    -0.07
     parsed
    -0.07
     Started
    -0.06
    终究
    -0.06
    践
    -0.06
    懈
    -0.06
    Uploaded
    -0.06
    푼
    -0.06
    POSITIVE LOGITS
     living
    0.07
    	IL
    0.07
    ⵉ
    0.07
     метал
    0.07
     Hil
    0.07
    针织
    0.07
    Elect
    0.07
    𝓲
    0.07
     Denis
    0.06
    (env
    0.06
    Act Density 0.001%

    No Known Activations