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

    Neuronpedia

    INDEX
    Explanations

    truth or choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    螺
    -0.07
    .fac
    -0.07
     přek
    -0.07
     З
    -0.06
     poner
    -0.06
     гриб
    -0.06
     Organizer
    -0.06
    новаж
    -0.06
    	RTHOOK
    -0.06
     Tanrı
    -0.06
    POSITIVE LOGITS
     매
    0.06
    です
    0.06
    инку
    0.06
     Pure
    0.06
    vely
    0.06
     jestli
    0.06
    {}{↵
    0.06
    autom
    0.06
     spider
    0.06
    acterial
    0.06
    Act Density 0.014%

    No Known Activations