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

    Neuronpedia

    INDEX
    Explanations

    PowerShell

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (weight
    -0.07
     amassed
    -0.06
    ],
    -0.06
     Bring
    -0.06
     transitioning
    -0.06
     scoop
    -0.06
    Alloc
    -0.06
     proudly
    -0.06
    (queue
    -0.06
    .actor
    -0.06
    POSITIVE LOGITS
    perfil
    0.07
     unborn
    0.07
     ['$
    0.07
     النظام
    0.07
    AAAAAAAA
    0.07
    writers
    0.06
    uela
    0.06
     허
    0.06
    명을
    0.06
    ullah
    0.06
    Act Density 0.005%

    No Known Activations