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

    Neuronpedia

    INDEX
    Explanations

    arme

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allows
    -0.06
     teaches
    -0.06
     stated
    -0.06
    edics
    -0.06
    Gender
    -0.06
     cheated
    -0.06
     aver
    -0.06
    有些
    -0.06
    egov
    -0.06
    Seek
    -0.06
    POSITIVE LOGITS
    Fizz
    0.07
     bestowed
    0.06
    _vlan
    0.06
    อล
    0.06
     mk
    0.06
     bağ
    0.06
    uteur
    0.06
     duvar
    0.06
    .fa
    0.06
    _MODE
    0.06
    Act Density 0.022%

    No Known Activations