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

    Neuronpedia

    INDEX
    Explanations

    Box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Apollo
    -0.06
     stealth
    -0.06
    sında
    -0.06
    kovou
    -0.06
    >("
    -0.06
    "L
    -0.06
     immune
    -0.06
    CHIP
    -0.06
     *_
    -0.06
    IS
    -0.06
    POSITIVE LOGITS
     учит
    0.06
    eding
    0.06
     стак
    0.06
     Here
    0.06
     péče
    0.06
    ювання
    0.06
    ourg
    0.06
    нач
    0.06
    fadeOut
    0.06
    gang
    0.06
    Act Density 0.005%

    No Known Activations