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

    Neuronpedia

    INDEX
    Explanations

    duplicate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pressed
    -0.07
     Objects
    -0.06
    apps
    -0.06
    <l
    -0.06
     objects
    -0.06
    035
    -0.06
     curtain
    -0.06
    _CONTROL
    -0.06
     chống
    -0.06
    optgroup
    -0.06
    POSITIVE LOGITS
     Duplicate
    0.10
     duplicate
    0.08
    ouse
    0.08
    _dup
    0.07
     Bachelor
    0.07
     humid
    0.07
    Duplicate
    0.07
    ska
    0.07
     〃
    0.07
    ели
    0.07
    Act Density 0.003%

    No Known Activations