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

    Neuronpedia

    INDEX
    Explanations

    конкрет

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Start
    -0.07
     너무
    -0.07
    -src
    -0.07
    ılmış
    -0.06
     luxurious
    -0.06
     Az
    -0.06
     Balt
    -0.06
     pel
    -0.06
     přeb
    -0.06
    ?>"></
    -0.06
    POSITIVE LOGITS
    OTOS
    0.07
    CT
    0.07
     CT
    0.06
     cd
    0.06
    adget
    0.06
     jumping
    0.06
     weapon
    0.06
    零
    0.06
    ackers
    0.06
     murderer
    0.06
    Act Density 0.003%

    No Known Activations