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

    Neuronpedia

    INDEX
    Explanations

    ins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SIGNAL
    -0.07
     Мініст
    -0.07
     MOR
    -0.07
    له
    -0.06
     Personnel
    -0.06
    ublisher
    -0.06
    Ol
    -0.06
     disgusted
    -0.06
    loy
    -0.06
    mul
    -0.06
    POSITIVE LOGITS
    uko
    0.06
    uka
    0.06
     expo
    0.06
     Reno
    0.06
    ails
    0.06
     plage
    0.06
    connection
    0.06
    osc
    0.06
    urve
    0.06
     manten
    0.06
    Act Density 0.000%

    No Known Activations