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

    Neuronpedia

    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beled
    -0.07
    ollar
    -0.06
     hi
    -0.06
     wegen
    -0.06
    _imm
    -0.06
    cancelled
    -0.06
     Müş
    -0.06
     energies
    -0.06
    .al
    -0.06
     llam
    -0.06
    POSITIVE LOGITS
     precedence
    0.07
     Le
    0.07
     Sho
    0.07
    專
    0.06
    Ρ
    0.06
    per
    0.06
     fabulous
    0.06
    �
    0.06
     drawer
    0.06
     Cathy
    0.06
    Act Density 0.001%

    No Known Activations