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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pozit
    -0.07
     Bea
    -0.07
    issent
    -0.07
     stacking
    -0.07
    Recent
    -0.07
    Interface
    -0.07
    reland
    -0.06
     compete
    -0.06
    vs
    -0.06
     Blur
    -0.06
    POSITIVE LOGITS
    よう
    0.07
     přest
    0.06
     Ernst
    0.06
    �
    0.06
    _MM
    0.06
     дальней
    0.06
     exits
    0.06
     mattress
    0.06
    iah
    0.06
     indifferent
    0.06
    Act Density 0.059%

    No Known Activations