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

    Neuronpedia

    INDEX
    Explanations

    short connecting words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )_
    -0.06
     cooler
    -0.06
    lemen
    -0.06
     curved
    -0.06
     srpna
    -0.06
     lille
    -0.06
     isol
    -0.06
     mus
    -0.06
     blogs
    -0.06
     Julius
    -0.06
    POSITIVE LOGITS
    _FINE
    0.08
     Nicaragua
    0.07
     đĩa
    0.07
     Єв
    0.07
     Chevrolet
    0.06
     misleading
    0.06
    ToRemove
    0.06
     charcoal
    0.06
     Sweet
    0.06
    ��
    0.06
    Act Density 0.000%

    No Known Activations