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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PLUGIN
    -0.07
     days
    -0.07
     hours
    -0.07
    	value
    -0.06
     condom
    -0.06
    819
    -0.06
     maka
    -0.06
    _ONE
    -0.06
    Numeric
    -0.06
    (token
    -0.06
    POSITIVE LOGITS
    	sprite
    0.07
     deutsche
    0.06
    /.↵
    0.06
    xab
    0.06
     Ná
    0.06
     внутри
    0.06
    áků
    0.06
    /world
    0.06
    语
    0.06
     newY
    0.06
    Act Density 0.025%

    No Known Activations