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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üph
    -0.07
    Intro
    -0.06
    _CONV
    -0.06
     marginBottom
    -0.06
    르는
    -0.06
    Reflection
    -0.06
    Prefab
    -0.06
    映画
    -0.06
     anarch
    -0.06
     예
    -0.06
    POSITIVE LOGITS
    802
    0.06
     λ
    0.06
    _bw
    0.06
    aggio
    0.06
    approval
    0.06
     bike
    0.06
     ((
    0.06
    	stats
    0.06
    (button
    0.06
     LLC
    0.06
    Act Density 0.027%

    No Known Activations