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

    Neuronpedia

    INDEX
    Explanations

    was/were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    secutive
    -0.07
    Normalized
    -0.06
    _rot
    -0.06
    bcc
    -0.06
     thr
    -0.06
    676
    -0.06
     erection
    -0.06
    ุท
    -0.06
    แล
    -0.06
    aec
    -0.06
    POSITIVE LOGITS
     }*/↵
    0.07
     política
    0.06
     berhasil
    0.06
     procent
    0.06
    (Canvas
    0.06
     Paolo
    0.06
     musel
    0.06
    ِل
    0.06
     space
    0.06
    ційної
    0.06
    Act Density 0.043%

    No Known Activations