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

    Neuronpedia

    INDEX
    Explanations

    ost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Edit
    -0.07
    apore
    -0.07
    にある
    -0.07
    .Config
    -0.07
     Defense
    -0.07
    街道
    -0.06
    "fmt
    -0.06
    _flutter
    -0.06
     JM
    -0.06
    /Page
    -0.06
    POSITIVE LOGITS
    //!
    0.07
    ि
    0.07
    pletion
    0.07
    +↵
    0.07
     underestimated
    0.07
     нач
    0.06
    0.06
     réal
    0.06
    _hal
    0.06
     incons
    0.06
    Act Density 0.006%
    No Known Activations