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

    Neuronpedia

    INDEX
    Explanations

    genetic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (=
    -0.07
    وله
    -0.07
    ForRow
    -0.06
    detalle
    -0.06
    ignant
    -0.06
     steadfast
    -0.06
     измер
    -0.06
    camel
    -0.06
     Unlike
    -0.06
    ]:↵↵
    -0.06
    POSITIVE LOGITS
     POT
    0.07
     Mandal
    0.07
     PF
    0.07
     diesen
    0.06
     ningún
    0.06
    /render
    0.06
     Mandatory
    0.06
     pot
    0.06
    �
    0.06
     APPLY
    0.06
    Act Density 0.031%

    No Known Activations