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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    phalt
    0.40
    Enc
    0.39
    Changes
    0.39
    angebot
    0.39
    vered
    0.39
    Pal
    0.38
    Appear
    0.36
    Edad
    0.36
    әт
    0.35
    Recording
    0.35
    POSITIVE LOGITS
    ញ
    0.42
     assemble
    0.40
     bribe
    0.39
     AB
    0.38
     ల
    0.37
     quicker
    0.37
     Nip
    0.37
     SAVE
    0.37
     primjer
    0.37
     steeple
    0.37
    Act Density 0.000%

    No Known Activations