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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Interior
    -0.07
    水平
    -0.07
    範
    -0.06
     displacement
    -0.06
    声
    -0.06
    鲁
    -0.06
    @"
    -0.06
     countryside
    -0.06
     modern
    -0.06
    해
    -0.06
    POSITIVE LOGITS
    /perl
    0.07
    	required
    0.07
    muş
    0.07
    >B
    0.07
     signings
    0.06
    -agent
    0.06
    .removeEventListener
    0.06
     Paginator
    0.06
     iktidar
    0.06
    _confirmation
    0.06
    Act Density 0.002%

    No Known Activations