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

    Neuronpedia

    INDEX
    Explanations

    good luck

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chtig
    0.44
    0.41
     damage
    0.40
    n
    0.39
    EN
    0.39
     acres
    0.39
     tree
    0.39
    i
    0.38
     establish
    0.37
    j
    0.37
    POSITIVE LOGITS
    بہ
    0.55
     бк
    0.53
     😁
    0.52
     Luffy
    0.52
    🔱
    0.52
    <unused510>
    0.51
     😎
    0.50
    <unused387>
    0.50
    <unused2031>
    0.50
    webserv
    0.50
    Act Density 0.001%

    No Known Activations