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

    Neuronpedia

    INDEX
    Explanations

    foreign scripts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vester
    -0.09
    تح
    -0.07
    师事务
    -0.07
     guarded
    -0.07
    igslist
    -0.07
    /comments
    -0.07
    tf
    -0.07
     NPCs
    -0.07
    	AT
    -0.07
     GFX
    -0.07
    POSITIVE LOGITS
    _usec
    0.08
     lengths
    0.07
    cats
    0.06
    📶
    0.06
     forecasting
    0.06
    匈奴
    0.06
    .blue
    0.06
     sliced
    0.06
    赋能
    0.06
     beaches
    0.06
    Act Density 0.025%

    No Known Activations