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

    Neuronpedia

    INDEX
    Explanations

    supplementary material

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vive
    -0.07
    hosts
    -0.07
     �
    -0.07
     EMC
    -0.06
    !
    -0.06
     Francesco
    -0.06
    ASSWORD
    -0.06
    (path
    -0.06
     Extract
    -0.06
    ml
    -0.06
    POSITIVE LOGITS
     Wenger
    0.07
    eggies
    0.07
    nEnter
    0.06
    imag
    0.06
    .rate
    0.06
    -deals
    0.06
    February
    0.06
     decency
    0.06
     arresting
    0.06
    ุมภาพ
    0.06
    Act Density 0.000%

    No Known Activations