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

    Neuronpedia

    INDEX
    Explanations

    nanomachines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     및
    -0.07
     всю
    -0.06
     Gems
    -0.06
     lan
    -0.06
    _outline
    -0.05
     ráp
    -0.05
     @{$
    -0.05
    }$
    -0.05
     departure
    -0.05
    _PART
    -0.05
    POSITIVE LOGITS
     вихов
    0.07
    ธน
    0.07
    stashop
    0.07
    [np
    0.07
    648
    0.06
     thận
    0.06
     sustain
    0.06
    537
    0.06
    ्ठ
    0.06
    ımızı
    0.06
    Act Density 0.020%

    No Known Activations