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

    Neuronpedia

    INDEX
    Explanations

    sequential steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Progress
    -0.07
    ».↵↵
    -0.07
    ¾
    -0.06
    ()])↵
    -0.06
     '(
    -0.06
    ].↵
    -0.06
    �
    -0.06
    	sprite
    -0.06
     otherButtonTitles
    -0.06
    	keys
    -0.06
    POSITIVE LOGITS
     Ре
    0.07
    ‏
    0.07
     Potion
    0.07
     Studi
    0.07
     Storm
    0.06
    rai
    0.06
    осудар
    0.06
    _tv
    0.06
     Περι
    0.06
     bom
    0.06
    Act Density 0.087%

    No Known Activations