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

    Neuronpedia

    INDEX
    Explanations

    Closing brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATIONAL
    -0.06
    worked
    -0.06
    intros
    -0.06
     constrained
    -0.06
     thêm
    -0.06
    repo
    -0.06
    �
    -0.06
    午
    -0.06
     nợ
    -0.06
     neler
    -0.06
    POSITIVE LOGITS
    (sig
    0.07
    elas
    0.07
    emb
    0.07
     distortion
    0.06
     inheritance
    0.06
     aque
    0.06
    zbollah
    0.06
    UIColor
    0.06
    nia
    0.06
     محل
    0.06
    Act Density 0.022%

    No Known Activations