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

    Neuronpedia

    INDEX
    Explanations

    time ranges with AM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viewpoint
    0.41
     localhost
    0.38
     setempat
    0.37
    anam
    0.36
     persona
    0.36
    ಡ್ಡ
    0.36
     medically
    0.35
     トー
    0.35
     દૂર
    0.35
    டத்தில்
    0.35
    POSITIVE LOGITS
    Denovo
    0.45
    Coef
    0.42
     kroppen
    0.40
     Syst
    0.40
    otive
    0.39
    ্মদ
    0.38
    otiv
    0.38
    DS
    0.38
    Syst
    0.38
    úsica
    0.37
    Act Density 0.004%

    No Known Activations