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

    Neuronpedia

    INDEX
    Explanations

    Writing and grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    q
    -0.07
     omas
    -0.07
    Medium
    -0.07
    execute
    -0.07
    -method
    -0.06
    -q
    -0.06
    iry
    -0.06
    rán
    -0.06
    ()+
    -0.06
    ností
    -0.06
    POSITIVE LOGITS
     DIST
    0.07
     вваж
    0.07
    WHO
    0.07
    .Unity
    0.07
     XIII
    0.06
     barric
    0.06
     Liz
    0.06
    ��
    0.06
    engage
    0.06
    ILT
    0.06
    Act Density 0.016%

    No Known Activations