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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roth
    -0.07
     feelings
    -0.07
    ��
    -0.06
     Rim
    -0.06
     fines
    -0.06
     Worm
    -0.06
      
↵
↵
    -0.06
    扣
    -0.06
    gam
    -0.06
     Containers
    -0.06
    POSITIVE LOGITS
     сах
    0.07
    _Id
    0.07
     objekt
    0.07
    ownik
    0.06
    ombies
    0.06
    ivatel
    0.06
     sonucu
    0.06
    ograd
    0.06
    iel
    0.06
    ossal
    0.06
    Act Density 0.061%

    No Known Activations