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

    Neuronpedia

    INDEX
    Explanations

    Altering behaviour or attraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pian
    -0.07
    .document
    -0.07
     bard
    -0.07
     stressful
    -0.06
    Constructed
    -0.06
    _POP
    -0.06
    ská
    -0.06
     Build
    -0.06
     Sequential
    -0.06
     listed
    -0.06
    POSITIVE LOGITS
     ошиб
    0.07
    昌
    0.06
     اندازه
    0.06
    捕
    0.06
    	gr
    0.06
    必要
    0.06
     مسجد
    0.06
    addGroup
    0.06
     seks
    0.06
    cle
    0.06
    Act Density 0.018%

    No Known Activations