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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thermo
    -0.07
     nights
    -0.07
    _info
    -0.07
    _param
    -0.07
     filming
    -0.06
     nederland
    -0.06
     싶
    -0.06
    -,
    -0.06
    NoSuch
    -0.06
    (configuration
    -0.06
    POSITIVE LOGITS
     tématu
    0.06
     gritty
    0.06
     letzten
    0.06
    итися
    0.06
    वर
    0.06
    _Image
    0.06
    мі
    0.06
    uniacid
    0.06
    ข
    0.06
     yiy
    0.06
    Act Density 0.035%

    No Known Activations