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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poons
    -0.07
    Sounds
    -0.07
    ader
    -0.06
     compr
    -0.06
    _version
    -0.06
     unmist
    -0.06
    .YesNo
    -0.06
    Initializer
    -0.06
    vre
    -0.06
     ван
    -0.06
    POSITIVE LOGITS
     Hotel
    0.07
    приєм
    0.06
     pdata
    0.06
    แข
    0.06
    мент
    0.06
     directional
    0.06
     letters
    0.05
     która
    0.05
    λμ
    0.05
     Finding
    0.05
    Act Density 0.011%

    No Known Activations