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

    Neuronpedia

    INDEX
    Explanations

    software projects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,-
    -0.07
    .Module
    -0.07
    (Action
    -0.06
    (Build
    -0.06
    уса
    -0.06
    _FACT
    -0.06
    (dynamic
    -0.06
    stry
    -0.06
     Duo
    -0.06
     coaching
    -0.06
    POSITIVE LOGITS
     odstran
    0.06
     Ül
    0.06
    rray
    0.06
    italic
    0.06
     yaptık
    0.06
    activo
    0.06
    ่ใช
    0.06
     récup
    0.06
     IMPLIED
    0.06
    merged
    0.06
    Act Density 0.118%

    No Known Activations