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

    Neuronpedia

    INDEX
    Explanations

    sharing, cooperation, social skills

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pédagog
    -0.09
     source
    -0.09
     familien
    -0.08
     termini
    -0.08
     istil
    -0.08
     Source
    -0.08
     astroph
    -0.08
     patients
    -0.08
    fatt
    -0.07
     unreachable
    -0.07
    POSITIVE LOGITS
    မျ
    0.09
    끼
    0.08
    _tv
    0.08
    �
    0.08
     gosta
    0.08
     Joining
    0.08
     التن
    0.08
     courteous
    0.08
     الاتجاه
    0.08
    ísmo
    0.08
    Act Density 0.021%

    No Known Activations