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

    Neuronpedia

    INDEX
    Explanations

    ode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     이유
    -0.07
    寄
    -0.06
     Ceremony
    -0.06
    ��
    -0.06
    Hand
    -0.06
     Was
    -0.06
     Workers
    -0.06
    709
    -0.06
     вред
    -0.06
    Ped
    -0.06
    POSITIVE LOGITS
     deformation
    0.06
    (()=>
    0.06
     heavens
    0.06
    )}>
    0.06
    _new
    0.06
     eslint
    0.06
    Meteor
    0.06
    ("__
    0.06
     plais
    0.06
    _Module
    0.06
    Act Density 0.000%

    No Known Activations