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

    Neuronpedia

    INDEX
    Explanations

    aforementioned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    รษฐ
    -0.07
    cro
    -0.07
    /modules
    -0.07
    dr
    -0.06
    mag
    -0.06
    intree
    -0.06
     crossing
    -0.06
    Central
    -0.06
    -Methods
    -0.06
     summer
    -0.06
    POSITIVE LOGITS
     aforementioned
    0.08
     aware
    0.07
    145
    0.07
     Troll
    0.07
    504
    0.07
     vistas
    0.07
     earnings
    0.07
    147
    0.06
    458
    0.06
    _ATTACK
    0.06
    Act Density 0.001%

    No Known Activations