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

    Neuronpedia

    INDEX
    Explanations

    TV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gon
    -0.07
    leon
    -0.07
    enth
    -0.07
     obedience
    -0.07
     Megan
    -0.07
    ящих
    -0.07
    elor
    -0.07
    ich
    -0.07
    atom
    -0.07
    buch
    -0.07
    POSITIVE LOGITS
     TV
    0.21
    TV
    0.14
     tv
    0.12
     Tv
    0.11
     TVs
    0.11
    Tv
    0.10
    .tv
    0.09
    tv
    0.08
    _tv
    0.08
    	tv
    0.07
    Act Density 0.008%

    No Known Activations