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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �除
    -0.07
    옄
    -0.07
    /sbin
    -0.07
     sweep
    -0.07
     להעביר
    -0.07
     suck
    -0.07
    ˲
    -0.07
    pieczeń
    -0.07
    扑
    -0.07
     stip
    -0.06
    POSITIVE LOGITS
     businesses
    0.08
     dependent
    0.07
     detectives
    0.07
     UIS
    0.07
    空军
    0.06
    或是
    0.06
    >[↵
    0.06
     Zeus
    0.06
    演唱
    0.06
     Depression
    0.06
    Act Density 0.011%

    No Known Activations