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

    Neuronpedia

    INDEX
    Explanations

    Lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ד
    -0.07
    FF
    -0.06
    �
    -0.06
    ,en
    -0.06
    ิญ
    -0.06
    τέρα
    -0.06
    HeaderInSection
    -0.06
     hei
    -0.06
    hoo
    -0.06
     RUNNING
    -0.06
    POSITIVE LOGITS
     Chart
    0.07
    isses
    0.07
     unauthorized
    0.06
    github
    0.06
     ideological
    0.06
    avatars
    0.06
     userid
    0.06
     Eight
    0.06
    larından
    0.06
    irsch
    0.06
    Act Density 0.207%

    No Known Activations