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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     робити
    -0.07
    rieving
    -0.07
     Bailey
    -0.06
    oodoo
    -0.06
    학과
    -0.06
     �
    -0.06
    'яз
    -0.06
    .Ui
    -0.06
    	em
    -0.06
    iedades
    -0.06
    POSITIVE LOGITS
     grote
    0.07
    ратег
    0.06
    Turkey
    0.06
     elbow
    0.06
    ��
    0.06
     Turkey
    0.06
     envision
    0.06
    Pane
    0.06
    les
    0.06
     ami
    0.06
    Act Density 0.048%

    No Known Activations