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

    Neuronpedia

    INDEX
    Explanations

    Code and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     глу
    -0.07
    ่ใช
    -0.07
    -cmpr
    -0.07
    λευτα
    -0.06
    rides
    -0.06
     sliding
    -0.06
     grund
    -0.06
     triple
    -0.06
     pensar
    -0.06
     nghiêm
    -0.06
    POSITIVE LOGITS
    ok
    0.07
     extrem
    0.07
     каждого
    0.07
    OK
    0.06
    osi
    0.06
    osexual
    0.06
    memset
    0.06
    ↵
↵
    0.06
    techn
    0.06
    Passwords
    0.06
    Act Density 0.000%

    No Known Activations