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

    Neuronpedia

    INDEX
    Explanations

    Ansible module parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🔷
    0.39
     chất
    0.36
     μο
    0.36
    …</
    0.35
     sing
    0.35
    łę
    0.35
    质量
    0.35
    ไหล
    0.34
    ீரி
    0.34
    Wel
    0.34
    POSITIVE LOGITS
    indar
    0.37
    Stat
    0.37
    sans
    0.37
    stat
    0.37
    saldo
    0.37
    xxxx
    0.36
    amerika
    0.36
     paar
    0.36
     fortr
    0.36
    ᕋ
    0.36
    Act Density 0.004%

    No Known Activations