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

    Neuronpedia

    INDEX
    Explanations

    fear and anxiety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Invitation
    0.40
    Vor
    0.39
    荣誉
    0.39
    RefreshToken
    0.37
    Fluid
    0.37
    rewards
    0.36
     effortless
    0.36
    邀请
    0.36
    欠
    0.36
    韵
    0.36
    POSITIVE LOGITS
     fear
    2.42
     panic
    2.28
     frightened
    2.28
     fearful
    2.27
     fears
    2.20
     scared
    2.14
    恐惧
    2.14
     Fear
    2.13
     terrified
    2.11
    Fear
    2.08
    Act Density 0.031%

    No Known Activations