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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    இ
    -0.07
     Micha
    -0.07
    invest
    -0.07
    investment
    -0.07
    ดวง
    -0.06
    .integration
    -0.06
     underscores
    -0.06
     Российской
    -0.06
     kilomet
    -0.06
    吐槽
    -0.06
    POSITIVE LOGITS
     phosphate
    0.08
    pectral
    0.07
     acct
    0.07
     liner
    0.07
     waar
    0.07
    _ctl
    0.06
    ланд
    0.06
    _probs
    0.06
    mkdir
    0.06
    ->[
    0.06
    Act Density 0.005%

    No Known Activations