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

    Neuronpedia

    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    胸前
    -0.07
    .High
    -0.07
    🛑
    -0.07
    📔
    -0.07
    .const
    -0.07
     rubbed
    -0.06
     Issues
    -0.06
     Selected
    -0.06
    /browse
    -0.06
    	Add
    -0.06
    POSITIVE LOGITS
     Warsaw
    0.07
    _inds
    0.07
    phants
    0.07
    indows
    0.06
     semantic
    0.06
     virtually
    0.06
    zyć
    0.06
    .margin
    0.06
    ゟ
    0.06
     };↵↵
    0.06
    Act Density 0.005%

    No Known Activations