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

    Neuronpedia

    INDEX
    Explanations

    clearing search input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apprenticeship
    -0.09
     trillion
    -0.07
    声
    -0.07
     �
    -0.07
    Allocate
    -0.07
    .allocate
    -0.07
    282
    -0.07
     gutt
    -0.07
     qualit
    -0.07
     esperar
    -0.07
    POSITIVE LOGITS
     sosyal
    0.08
    uchtung
    0.08
    بطال
    0.08
     elección
    0.07
    cing
    0.07
     ditu
    0.07
     oči
    0.07
    服务热线
    0.07
     показывает
    0.07
    0.07
    Act Density 0.001%
    No Known Activations