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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     край
    -0.07
     mệ
    -0.06
     tim
    -0.06
    (App
    -0.06
    /lists
    -0.06
     ro
    -0.06
    dojo
    -0.06
     Bake
    -0.06
     dle
    -0.06
    ैन
    -0.06
    POSITIVE LOGITS
     Reliable
    0.07
     Vintage
    0.07
    Modifiers
    0.07
    ytt
    0.07
     deceived
    0.06
    .pr
    0.06
     остав
    0.06
    _orientation
    0.06
    egative
    0.06
    454
    0.06
    Act Density 0.000%

    No Known Activations