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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sliced
    -0.07
     cuz
    -0.07
     eldre
    -0.07
     ओ
    -0.06
    /stream
    -0.06
    Okay
    -0.06
     också
    -0.06
    gether
    -0.06
    ropolitan
    -0.06
     cows
    -0.06
    POSITIVE LOGITS
    	Command
    0.08
    encing
    0.07
    _mutex
    0.07
    _SINGLE
    0.07
     §
    0.07
    لال
    0.07
    -Version
    0.07
     this
    0.06
    LANG
    0.06
     passive
    0.06
    Act Density 0.000%

    No Known Activations