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

    Neuronpedia

    INDEX
    Explanations

    avoid settling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IamPermissions
    0.47
     instituições
    0.46
     |-
    0.45
     테
    0.41
     孔
    0.41
    кг
    0.40
    ;|&
    0.39
     ack
    0.39
     ")"
    0.39
     Departments
    0.39
    POSITIVE LOGITS
     was
    0.43
     indistinct
    0.42
    Television
    0.39
     pictured
    0.38
     tranquil
    0.37
    aysia
    0.37
    Ban
    0.37
    Ꮴ
    0.36
     kicks
    0.36
    רית
    0.36
    Act Density 0.000%

    No Known Activations