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

    Neuronpedia

    INDEX
    Explanations

    deleting elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     z
    -0.06
    üle
    -0.06
     فتح
    -0.06
    UNET
    -0.06
    termination
    -0.06
    Rand
    -0.06
     jov
    -0.06
    _oid
    -0.05
     lập
    -0.05
    -0.05
    POSITIVE LOGITS
     Courses
    0.08
     conson
    0.07
    -rock
    0.07
     volcan
    0.07
     enchant
    0.07
    aincontri
    0.07
    особ
    0.06
    iciary
    0.06
     Tot
    0.06
    mentor
    0.06
    Act Density 0.030%

    No Known Activations