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

    Neuronpedia

    INDEX
    Explanations

    Llama model sizes (7B, 13B, 70B)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estadounidense
    0.46
     ghost
    0.42
     modos
    0.42
     flame
    0.42
     sword
    0.42
    炯
    0.41
     parabol
    0.40
    உ
    0.40
    ټبال
    0.40
    ظل
    0.40
    POSITIVE LOGITS
    update
    0.50
    idn
    0.49
     बरेली
    0.46
    unat
    0.46
    nr
    0.45
     zusätz
    0.45
    enio
    0.45
     वनस्पती
    0.45
    invite
    0.44
    urities
    0.44
    Act Density 0.001%

    No Known Activations