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

    Neuronpedia

    INDEX
    Explanations

    pip install

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जिज्ञा
    0.79
     加入
    0.77
     নিঃসৃত
    0.76
    Referencias
    0.74
    র্বর
    0.73
     ফের
    0.73
     divulgação
    0.70
     (_,
    0.70
    吳
    0.70
     Computation
    0.69
    POSITIVE LOGITS
     install
    1.31
    install
    1.08
     installing
    1.07
    Installing
    1.01
     ins
    1.01
     Install
    0.99
     installs
    0.98
     uninstall
    0.98
    Install
    0.98
     installations
    0.98
    Act Density 0.029%

    No Known Activations