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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :])
    -0.07
     sensual
    -0.07
    )))))↵
    -0.07
     Lair
    -0.07
     perch
    -0.07
     zus
    -0.06
     Sets
    -0.06
     Gö
    -0.06
     inici
    -0.06
     speci
    -0.06
    POSITIVE LOGITS
    上
    0.07
    _accessible
    0.07
    iky
    0.06
     Dave
    0.06
     minX
    0.06
    �
    0.06
    农
    0.06
    Occ
    0.06
     prevalent
    0.06
     kvp
    0.06
    Act Density 0.000%

    No Known Activations