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

    Neuronpedia

    INDEX
    Explanations

    Silos and isolation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plement
    -0.07
     Brunswick
    -0.07
     shalt
    -0.06
    екту
    -0.06
    ags
    -0.06
    œur
    -0.06
    子
    -0.06
     ecology
    -0.06
    release
    -0.06
     "*"
    -0.06
    POSITIVE LOGITS
    ิร
    0.06
    矿
    0.06
     své
    0.06
    严
    0.06
    ้าร
    0.06
     vytvá
    0.06
     문
    0.06
    (Role
    0.06
     thành
    0.06
    _ASSOC
    0.06
    Act Density 0.010%

    No Known Activations