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

    Neuronpedia

    INDEX
    Explanations

    pop ap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /pro
    -0.07
     thủy
    -0.07
    ゴ
    -0.07
    send
    -0.07
    шего
    -0.06
    -width
    -0.06
    eq
    -0.06
    pes
    -0.06
    ข
    -0.06
     gx
    -0.06
    POSITIVE LOGITS
     подав
    0.07
     POP
    0.06
     grassroots
    0.06
     replicas
    0.06
     đáng
    0.06
     kvinn
    0.06
    avage
    0.06
    alaria
    0.06
     Customs
    0.06
     percept
    0.06
    Act Density 0.004%

    No Known Activations