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

    Neuronpedia

    INDEX
    Explanations

    connecting words/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consequ
    -0.06
    GroupName
    -0.06
     Leh
    -0.06
    宅
    -0.06
     crossings
    -0.06
     banker
    -0.06
    itations
    -0.06
     Argument
    -0.06
    infer
    -0.06
     घ
    -0.05
    POSITIVE LOGITS
    _SI
    0.07
     JMP
    0.07
    ясь
    0.07
     SPI
    0.07
    MPI
    0.07
    vrolet
    0.06
    .system
    0.06
    ="/
    0.06
    _BITS
    0.06
     프리
    0.06
    Act Density 0.175%

    No Known Activations