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

    Neuronpedia

    INDEX
    Explanations

    Ne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $L
    -0.07
    |r
    -0.07
    +f
    -0.07
    Dies
    -0.07
    HRESULT
    -0.07
    +y
    -0.07
    [g
    -0.06
     MODIFY
    -0.06
     sacr
    -0.06
     continuum
    -0.06
    POSITIVE LOGITS
     Neptune
    0.08
    ніп
    0.07
     reun
    0.07
     neut
    0.07
     Ne
    0.07
     Nec
    0.06
    และ
    0.06
    -he
    0.06
     Treasure
    0.06
     neod
    0.06
    Act Density 0.091%

    No Known Activations