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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obsolete
    -0.07
    Sim
    -0.06
    �
    -0.06
     derec
    -0.06
     unilateral
    -0.06
    defgroup
    -0.06
     Helsinki
    -0.06
     warns
    -0.06
     metabol
    -0.06
    atatype
    -0.06
    POSITIVE LOGITS
     Irene
    0.07
    ENTER
    0.07
    ();↵
    0.06
     Ocak
    0.06
     confuse
    0.06
     INV
    0.06
     кож
    0.06
    alama
    0.06
     rest
    0.06
    著
    0.06
    Act Density 0.022%

    No Known Activations