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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    คว
    -0.07
    煓
    -0.06
     attire
    -0.06
    募集资金
    -0.06
     He
    -0.06
    𬭳
    -0.06
     gaussian
    -0.06
     commanded
    -0.06
     commentator
    -0.06
    $val
    -0.06
    POSITIVE LOGITS
     מג
    0.07
     Narc
    0.07
     GO
    0.07
     AB
    0.07
     RIP
    0.07
    半个
    0.07
     outbreak
    0.07
     Rae
    0.06
     PHP
    0.06
     Alberto
    0.06
    Act Density 0.003%

    No Known Activations