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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    annes
    -0.07
    .off
    -0.06
    cribes
    -0.06
     или
    -0.06
    ERTICAL
    -0.06
    通过
    -0.06
     GPS
    -0.06
    emp
    -0.06
    .Screen
    -0.06
    affles
    -0.06
    POSITIVE LOGITS
    Frank
    0.07
     quello
    0.07
    ±n
    0.07
     sele
    0.07
     parenthesis
    0.07
     SLOT
    0.06
     Killer
    0.06
    'aff
    0.06
    še
    0.06
     เซ
    0.06
    Act Density 0.005%

    No Known Activations