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

    Neuronpedia

    INDEX
    Explanations

    Instructions to find something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adolescente
    -0.06
    izontal
    -0.06
    ��
    -0.06
    韓
    -0.06
    از
    -0.06
     马
    -0.06
     Bobby
    -0.06
    Triple
    -0.06
    ังไม
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     polite
    0.07
    _VERBOSE
    0.06
    .Display
    0.06
    %D
    0.06
    -native
    0.06
    .te
    0.06
     dismissing
    0.06
     smirk
    0.06
     Stone
    0.06
    che
    0.06
    Act Density 0.038%

    No Known Activations