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

    Neuronpedia

    INDEX
    Explanations

    phrases with common continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aparte
    0.42
    espace
    0.42
     Surely
    0.40
    Surely
    0.40
    '=>$
    0.40
    sure
    0.38
    inside
    0.38
    "=>$
    0.38
    Initialized
    0.37
    ᅣ
    0.37
    POSITIVE LOGITS
     Disease
    0.40
    钞
    0.38
    珑
    0.38
    镍
    0.38
     fever
    0.36
     Flutter
    0.36
     Island
    0.36
     doodle
    0.36
     facies
    0.36
     Bill
    0.36
    Act Density 0.000%

    No Known Activations