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

    Neuronpedia

    INDEX
    Explanations

    criticism and critique

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    僥
    0.44
     toggle
    0.42
     تعیین
    0.41
     togg
    0.40
    AudioAsset
    0.39
     অনিশ্চ
    0.37
     اندراج
    0.37
    Permissions
    0.37
    庤
    0.37
    侥
    0.37
    POSITIVE LOGITS
     criticism
    3.36
     criticisms
    3.08
     criticize
    3.06
    critic
    3.06
     critique
    3.03
     Criticism
    3.03
    Critic
    3.00
     criticise
    2.94
    批评
    2.86
     critic
    2.84
    Act Density 0.127%

    No Known Activations