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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EXTI
    -0.07
    _As
    -0.06
    VELO
    -0.06
     Tro
    -0.06
     melanch
    -0.06
    Tro
    -0.06
    tro
    -0.06
     Riders
    -0.06
    薩
    -0.06
    	Class
    -0.06
    POSITIVE LOGITS
     lic
    0.07
    =(↵
    0.07
    icate
    0.07
    _syn
    0.06
    .comments
    0.06
     dik
    0.06
     od
    0.06
     dismissal
    0.06
     deletes
    0.06
    /single
    0.06
    Act Density 0.003%

    No Known Activations