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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fort
    -0.07
    атків
    -0.06
    (Runtime
    -0.06
    ibold
    -0.06
    arming
    -0.06
    nid
    -0.06
    аниц
    -0.06
    eld
    -0.06
    inity
    -0.06
    inds
    -0.06
    POSITIVE LOGITS
     stand
    0.07
     مج
    0.07
     shower
    0.07
     Assistance
    0.06
     tmp
    0.06
     cooperate
    0.06
    acer
    0.06
    ---↵
    0.06
    .cluster
    0.06
     Movie
    0.06
    Act Density 0.003%

    No Known Activations