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

    Neuronpedia

    INDEX
    Explanations

    contends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aproxim
    -0.07
    receipt
    -0.07
    Agregar
    -0.06
    airro
    -0.06
    ota
    -0.06
    alarda
    -0.06
    venes
    -0.06
    _PUS
    -0.06
     tran
    -0.06
    groupid
    -0.06
    POSITIVE LOGITS
    .imageView
    0.07
    onet
    0.07
     Fuse
    0.07
     shorts
    0.06
     mediator
    0.06
    erve
    0.06
    erved
    0.06
     Size
    0.06
     disadvantaged
    0.06
     check
    0.06
    Act Density 0.008%

    No Known Activations