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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ygons
    -0.08
    bedarf
    -0.08
     떠
    -0.08
    .nio
    -0.07
    মূল
    -0.07
     Vertrauen
    -0.07
    uo
    -0.07
     cartões
    -0.07
     Disk
    -0.07
    asons
    -0.07
    POSITIVE LOGITS
     ojo
    0.10
     designate
    0.09
     obligación
    0.09
     escapar
    0.08
     chupe
    0.08
    Mandatory
    0.08
     obrig
    0.08
     obligatorio
    0.08
     incluir
    0.08
     חובה
    0.08
    Act Density 0.010%

    No Known Activations